Paper Digest: Recent Papers on Generative Adversarial Network
Paper Digest Team extracted all recent Generative Adversarial Network (GAN) related papers on our radar, and generated highlight sentences for them. The results are then sorted by relevance & date. In addition to this ‘static’ page, we also provide a real-time version of this article, which has more coverage and is updated in real time to include the most recent updates on this topic. Based in New York, Paper Digest is dedicated to producing high-quality text analysis results that people can acturally use on a daily basis. In the past 4 years, we have been serving users across the world with a number of exclusive services on ranking, search, tracking and review. This month we feature Literature Review Generator, which automatically generates literature review around any topic.
If you do not want to miss any interesting academic paper, you are welcome to sign up our free daily paper digest service to get updates on new papers published in your area every day. You are also welcome to follow us on Twitter and Linkedin to get updated with new conference digests.
Paper Digest Team
team@paperdigest.org
TABLE 1: Paper Digest: Recent Papers on Generative Adversarial Network
| Paper | Author(s) | Source | Date | |
|---|---|---|---|---|
| 1 | GAN-based Matrix Factorization for Recommender Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we propose a new GAN-based approach that learns user and item latent factors in a matrix factorization setting for the generic top-N recommendation problem. |
Ervin Dervishaj; Paolo Cremonesi; | arxiv-cs.IR | 2022-01-20 |
| 2 | Learning-based Hybrid Local Search for The Hard-label Textual Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this observation, we propose a novel hard-label attack, called Learning-based Hybrid Local Search (LHLS) algorithm, which effectively estimates word importance with the prediction label from the attack history and integrate such information into hybrid local search algorithm to optimize the adversarial perturbation. |
Zhen Yu; Xiaosen Wang; Wanxiang Che; Kun He; | arxiv-cs.CL | 2022-01-20 |
| 3 | Simpler Is Better: Spectral Regularization and Up-sampling Techniques for Variational Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a simple 2D Fourier transform-based spectral regularization loss for the VAE and show that it can achieve results equal to, or better than, the current state-of-the-art in frequency-aware losses for generative models. |
Sara Björk; Jonas Nordhaug Myhre; Thomas Haugland Johansen; | arxiv-cs.LG | 2022-01-19 |
| 4 | A Survey on Training Challenges in Generative Adversarial Networks for Biomedical Image Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents a review and taxonomy based on solutions to the training problems of GANs in the biomedical imaging domain. |
Muhammad Muneeb Saad; Ruairi O’Reilly; Mubashir Husain Rehmani; | arxiv-cs.LG | 2022-01-19 |
| 5 | Autoencoding Video Latents for Adversarial Video Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we propose to autoencode the motion and appearance latent vectors of the video generator in the adversarial setting. |
Sai Hemanth Kasaraneni; | arxiv-cs.CV | 2022-01-18 |
| 6 | Minimax Optimality (Probably) Doesn’t Imply Distribution Learning for GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that standard cryptographic assumptions imply that this stronger condition is still insufficient. |
Sitan Chen; Jerry Li; Yuanzhi Li; Raghu Meka; | arxiv-cs.LG | 2022-01-18 |
| 7 | Contextual Road Lane and Symbol Generation for Autonomous Driving Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present a novel approach for lane detection and segmentation using generative models. |
Ajay Soni; Pratik Padamwar; Krishna Reddy Konda; | arxiv-cs.CV | 2022-01-18 |
| 8 | Variational Autoencoder Generative Adversarial Network for Synthetic Data Generation in Smart Home Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, in this paper, we propose a Variational AutoEncoder Generative Adversarial Network (VAE-GAN) as a smart grid data generative model which is capable of learning various types of data distributions and generating plausible samples from the same distribution without performing any prior analysis on the data before the training phase.We compared the Kullback-Leibler (KL) divergence, maximum mean discrepancy (MMD), and Wasserstein distance between the synthetic data (electrical load and PV production) distribution generated by the proposed model, vanilla GAN network, and the real data distribution, to evaluate the performance of our model. |
Mina Razghandi; Hao Zhou; Melike Erol-Kantarci; Damla Turgut; | arxiv-cs.LG | 2022-01-18 |
| 9 | Hardware-Efficient Deconvolution-Based GAN for Edge Computing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we proposed an HW/SW co-design approach for training quantized deconvolution GAN (QDCGAN) implemented on FPGA using a scalable streaming dataflow architecture capable of achieving higher throughput versus resource utilization trade-off. |
Azzam Alhussain; Mingjie Lin; | arxiv-cs.LG | 2022-01-18 |
| 10 | Adversarial Vulnerability of Powerful Near Out-of-distribution Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we demonstrate severe adversarial vulnerability on the challenging near OOD CIFAR-100 vs CIFAR-10 task, as well as on the far OOD CIFAR-100 vs SVHN. |
Stanislav Fort; | arxiv-cs.LG | 2022-01-18 |
| 11 | Collapse By Conditioning: Training Class-conditional GANs with Limited Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this observation, we propose a training strategy for conditional GANs (cGANs) that effectively prevents the observed mode-collapse by leveraging unconditional learning. |
Mohamad Shahbazi; Martin Danelljan; Danda Pani Paudel; Luc Van Gool; | arxiv-cs.CV | 2022-01-17 |
| 12 | Lifelong Generative Learning Via Knowledge Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we develop an efficient and effective lifelong generative model based on variational autoencoder (VAE). |
Libo Huang; Zhulin An; Xiang Zhi; Yongjun Xu; | arxiv-cs.LG | 2022-01-17 |
| 13 | SigGAN : Adversarial Model for Learning Signed Relationships in Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the recent success of Generative Adversarial Network (GAN) based models which comprises of a discriminator and generator in several applications, we propose a Generative Adversarial Network (GAN) based model for signed networks, SigGAN. |
Roshni Chakraborty; Ritwika Das; Joydeep Chandra; | arxiv-cs.SI | 2022-01-17 |
| 14 | Can We Find Neurons That Cause Unrealistic Images in Deep Generative Networks? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Research to determine why the artifacts emerge and how they can be detected and removed has not been sufficiently carried out. |
Hwanil Choi; Wonjoon Chang; Jaesik Choi; | arxiv-cs.CV | 2022-01-17 |
| 15 | Fully Convolutional Change Detection Framework with Generative Adversarial Network for Unsupervised, Weakly Supervised and Regional Supervised Change Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we proposed a fully convolutional change detection framework with generative adversarial network, to conclude unsupervised, weakly supervised, regional supervised, and fully supervised change detection tasks into one framework. |
Chen Wu; Bo Du; Liangpei Zhang; | arxiv-cs.CV | 2022-01-16 |
| 16 | Adversarial Machine Learning Threat Analysis in Open Radio Access Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a systematic AML threat analysis for the O-RAN. |
RON BITTON et. al. | arxiv-cs.CR | 2022-01-16 |
| 17 | ALA: Adversarial Lightness Attack Via Naturalness-aware Regularizations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To generate unrestricted adversarial examples with high image quality and good transferability, in this paper, we propose Adversarial Lightness Attack (ALA), a white-box unrestricted adversarial attack that focuses on modifying the lightness of the images. |
LIANGRU SUN et. al. | arxiv-cs.CV | 2022-01-16 |
| 18 | Conditional Variational Autoencoder with Balanced Pre-training for Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel Conditional Variational Autoencoder with Balanced Pre-training for Generative Adversarial Networks (CAPGAN) as an augmentation tool to generate realistic synthetic images. |
YUCHONG YAO et. al. | arxiv-cs.CV | 2022-01-13 |
| 19 | The Effectiveness of Time Stretching for Enhancing Dysarthric Speech for Improved Dysarthric Speech Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate several existing and a new state-of-the-art generative adversarial network-based (GAN) voice conversion method for enhancing dysarthric speech for improved dysarthric speech recognition. |
Luke Prananta; Bence Mark Halpern; Siyuan Feng; Odette Scharenborg; | arxiv-cs.SD | 2022-01-13 |
| 20 | Privacy-Utility Trades in Crowdsourced Signal Map Obfuscation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To examine this privacy-utility tradeoff, we identify privacy and utility metrics and threat models suited to signal strength measurements. |
Jiang Zhang; Lillian Clark; Matthew Clark; Konstantinos Psounis; Peter Kairouz; | arxiv-cs.CR | 2022-01-12 |
| 21 | Adversarially Robust Classification By Conditional Generative Model Inversion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a classification model that does not obfuscate gradients and is robust by construction without assuming prior knowledge about the attack. |
Mitra Alirezaei; Tolga Tasdizen; | arxiv-cs.LG | 2022-01-12 |
| 22 | BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Through an extensive ablation study we show big gains in leveraging a large generated dataset to train different supervised and self-supervised backbone models on pixel-wise tasks. |
DAIQING LI et. al. | arxiv-cs.CV | 2022-01-12 |
| 23 | Music2Video: Automatic Generation of Music Video with Fusion of Audio and Text Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on the fusion of text and audio, we create video whose content is consistent with the distinct modalities that are provided. |
Joel Jang; Sumin Shin; Yoonjeon Kim; | arxiv-cs.SD | 2022-01-11 |
| 24 | Deep Clustering with Fusion Autoencoder Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a novel DC method is proposed to address this issue. |
Shuai Chang; | arxiv-cs.LG | 2022-01-11 |
| 25 | FedDTG:Federated Data-Free Knowledge Distillation Via Three-Player Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a distributed three-player GAN to implement datafree co-distillation between clients. |
Zhenyuan Zhang; | arxiv-cs.LG | 2022-01-10 |
| 26 | Differentiable and Scalable Generative Adversarial Models for Data Imputation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an effective scalable imputation system named SCIS to significantly speed up the training of the differentiable generative adversarial imputation models under accuracy-guarantees for large-scale incomplete data. |
Yangyang Wu; Jun Wang; Xiaoye Miao; Wenjia Wang; Jianwei Yin; | arxiv-cs.LG | 2022-01-10 |
| 27 | GMFIM: A Generative Mask-guided Facial Image Manipulation Model for Privacy Preservation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Generative Mask-guided Face Image Manipulation (GMFIM) model based on GANs to apply imperceptible editing to the input face image to preserve the privacy of the person in the image. |
Mohammad Hossein Khojaste; Nastaran Moradzadeh Farid; Ahmad Nickabadi; | arxiv-cs.CV | 2022-01-10 |
| 28 | Differentially Private Generative Adversarial Networks with Model Inversion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Differentially Private Model Inversion (DPMI) method where the private data is first mapped to the latent space via a public generator, followed by a lower-dimensional DP-GAN with better convergent properties. |
Dongjie Chen; Sen-ching Samson Cheung; Chen-Nee Chuah; Sally Ozonoff; | arxiv-cs.LG | 2022-01-09 |
| 29 | Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose a novel framework for automated breaking of dark web CAPTCHA to facilitate dark web data collection. |
Ning Zhang; Mohammadreza Ebrahimi; Weifeng Li; Hsinchun Chen; | arxiv-cs.CV | 2022-01-08 |
| 30 | GenLabel: Mixup Relabeling Using Generative Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To resolve this, we propose GenLabel, a simple yet effective relabeling algorithm designed for mixup. |
JY-YONG SOHN et. al. | arxiv-cs.LG | 2022-01-07 |
| 31 | Realistic Full-Body Anonymization with Surface-Guided GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new anonymization method that generates close-to-photorealistic humans for in-the-wild images.A key part of our design is to guide adversarial nets by dense pixel-to-surface correspondences between an image and a canonical 3D surface.We introduce Variational Surface-Adaptive Modulation (V-SAM) that embeds surface information throughout the generator.Combining this with our novel discriminator surface supervision loss, the generator can synthesize high quality humans with diverse appearance in complex and varying scenes.We show that surface guidance significantly improves image quality and diversity of samples, yielding a highly practical generator.Finally, we demonstrate that surface-guided anonymization preserves the usability of data for future computer vision development |
Håkon Hukkelås; Morten Smebye; Rudolf Mester; Frank Lindseth; | arxiv-cs.CV | 2022-01-06 |
| 32 | Culture-to-Culture Image Translation with Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article introduces the concept of image culturization, i.e., defined as the process of altering the brushstroke of cultural features that make objects perceived as belonging to a given culture while preserving their functionalities. |
Giulia Zaino; Carmine Tommaso Recchiuto; Antonio Sgorbissa; | arxiv-cs.CV | 2022-01-05 |
| 33 | Biphasic Face Photo-Sketch Synthesis Via Semantic-Driven Generative Adversarial Network with Graph Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a novel Semantic-Driven Generative Adversarial Network to address the above issues, cooperating with the Graph Representation Learning. |
Xingqun Qi; Muyi Sun; Qi Li; Caifeng Shan; | arxiv-cs.CV | 2022-01-05 |
| 34 | Adversarial Robustness in Cognitive Radio Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The principle of byzantine resilience distributed hypothesis testing (BRDHT) is considered in this paper for cognitive radio networks (CRNs) $-$ without-loss-of-generality, something that can be extended to any type of homogeneous or heterogeneous networks. |
Makan Zamanipour; | arxiv-cs.IT | 2022-01-05 |
| 35 | Corrupting Data to Remove Deceptive Perturbation: Using Preprocessing Method to Improve System Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a new approach to improve neural network robustness by applying the recovery process on top of the naturally trained classifier. |
Hieu Le; Hans Walker; Dung Tran; Peter Chin; | arxiv-cs.CV | 2022-01-04 |
| 36 | On The Minimal Adversarial Perturbation for Deep Neural Networks with Provable Estimation Error Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper addresses this issue by proposing two lightweight strategies to find the minimal adversarial perturbation. |
Fabio Brau; Giulio Rossolini; Alessandro Biondi; Giorgio Buttazzo; | arxiv-cs.LG | 2022-01-04 |
| 37 | Towards Understanding and Harnessing The Effect of Image Transformation in Adversarial Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we systematically synthesize the recent progress on adversarial detection via image transformations with a novel classification method. |
Hui Liu; Bo Zhao; Yuefeng Peng; Weidong Li; Peng Liu; | arxiv-cs.CV | 2022-01-04 |
| 38 | Neural Network Training Under Semidefinite Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address this challenge by developing interior point methods for NN training that we implement using barrier functions for semidefinite constraints. |
Patricia Pauli; Niklas Funcke; Dennis Gramlich; Mohamed Amine Msalmi; Frank Allgöwer; | arxiv-cs.LG | 2022-01-03 |
| 39 | Actor-Critic Network for Q&A in An Adversarial Environment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces an approach that joins these two ideas together to train a critic model for use in an almost reinforcement learning framework. |
Bejan Sadeghian; | arxiv-cs.CL | 2022-01-02 |
| 40 | on The Effectiveness of Generative Adversarial Network on Anomaly Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Following this analogy, we suggested a new unsupervised model based on GANs –a combination of an autoencoder and a GAN. |
Laya Rafiee Sevyeri; Thomas Fevens; | arxiv-cs.LG | 2021-12-31 |
| 41 | Adversarial Attack Via Dual-Stage Network Erosion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, this paper proposes to improve the transferability of adversarial examples, and applies dual-stage feature-level perturbations to an existing model to implicitly create a set of diverse models. |
YEXIN DUAN et. al. | arxiv-cs.CV | 2021-12-31 |
| 42 | SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we present a 3D shape synthesis framework (SurfGen) that directly applies adversarial training to the object surface. |
Andrew Luo; Tianqin Li; Wen-Hao Zhang; Tai Sing Lee; | arxiv-cs.CV | 2021-12-31 |
| 43 | Overcoming Mode Collapse with Adaptive Multi Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this observation, we introduce a novel training procedure that adaptively spawns additional discriminators to remember previous modes of generation. |
Karttikeya Mangalam; Rohin Garg; | arxiv-cs.CV | 2021-12-29 |
| 44 | Learning Inception Attention for Image Synthesis and Image Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the well-known split-transform-aggregate design heuristic in the Inception building block, this paper proposes a Skip-Layer Inception Module (SLIM) that facilitates efficient learning of image synthesis models, and a same-layer variant (dubbed as SLIM too) as a stronger alternative to the well-known ResNeXts for image recognition. |
Jianghao Shen; Tianfu Wu; | arxiv-cs.CV | 2021-12-29 |
| 45 | FRIDA — Generative Feature Replay for Incremental Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We tackle the novel problem of incremental unsupervised domain adaptation (IDA) in this paper. |
SAYAN RAKSHIT et. al. | arxiv-cs.CV | 2021-12-28 |
| 46 | Adversarial Attack for Asynchronous Event-based Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our algorithm achieves an attack success rate of 97.95\% on the N-Caltech101 dataset. |
Wooju Lee; Hyun Myung; | arxiv-cs.CV | 2021-12-27 |
| 47 | Perlin Noise Improve Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Combined with the defensive idea of adversarial training, we use Perlin noise to train the neural network to obtain a model that can defend against procedural noise adversarial examples. |
Chengjun Tang; Kun Zhang; Chunfang Xing; Yong Ding; Zengmin Xu; | arxiv-cs.LG | 2021-12-26 |
| 48 | Invertible Network for Unpaired Low-light Image Enhancement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose to leverage the invertible network to enhance low-light image in forward process and degrade the normal-light one inversely with unpaired learning. |
Jize Zhang; Haolin Wang; Xiaohe Wu; Wangmeng Zuo; | arxiv-cs.CV | 2021-12-24 |
| 49 | Comparison and Analysis of Image-to-Image Generative Adversarial Networks: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we survey and analyze eight Image-to-Image Generative Adversarial Networks: Pix2Px, CycleGAN, CoGAN, StarGAN, MUNIT, StarGAN2, DA-GAN, and Self Attention GAN. |
Sagar Saxena; Mohammad Nayeem Teli; | arxiv-cs.CV | 2021-12-23 |
| 50 | Manifold Learning Benefits GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we improve Generative Adversarial Networks by incorporating a manifold learning step into the discriminator. |
Yao Ni; Piotr Koniusz; Richard Hartley; Richard Nock; | arxiv-cs.CV | 2021-12-23 |
| 51 | Cluster-guided Image Synthesis with Unconditional Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we focus on controllable image generation by leveraging GANs that are well-trained in an unsupervised fashion. |
Markos Georgopoulos; James Oldfield; Grigorios G Chrysos; Yannis Panagakis; | arxiv-cs.CV | 2021-12-23 |
| 52 | Generating Synthetic Mixed-type Longitudinal Electronic Health Records for Artificial Intelligent Applications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a generative adversarial network (GAN) entitled EHR-M-GAN which synthesizes \textit{mixed-type} timeseries EHR data. |
Jin Li; Benjamin J. Cairns; Jingsong Li; Tingting Zhu; | arxiv-cs.LG | 2021-12-22 |
| 53 | DA-FDFtNet: Dual Attention Fake Detection Fine-tuning Network to Detect Various AI-Generated Fake Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Dual Attention Fake Detection Fine-tuning Network (DA-FDFtNet) to detect the manipulated fake face images from the real face data. |
Young Oh Bang; Simon S. Woo; | arxiv-cs.CV | 2021-12-22 |
| 54 | Catch Me If You GAN: Using Artificial Intelligence for Fake Log Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: More precisely, three different generative adversarial networks, SeqGAN, MaliGAN, and CoT, are reviewed in this research regarding their performance, focusing on generating new logs as a means of deceiving system admins for red teams. |
Christian Toemmel; | arxiv-cs.CR | 2021-12-22 |
| 55 | Detect & Reject for Transferability of Black-box Adversarial Attacks Against Network Intrusion Detection Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the transferability of adversarial network traffic against multiple machine learning-based intrusion detection systems. |
Islam Debicha; Thibault Debatty; Jean-Michel Dricot; Wim Mees; Tayeb Kenaza; | arxiv-cs.CR | 2021-12-22 |
| 56 | Multiple Imputation Via Generative Adversarial Network for High-dimensional Blockwise Missing Value Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Multiple Imputation via Generative Adversarial Network (MI-GAN), a deep learning-based (in specific, a GAN-based) multiple imputation method, that can work under missing at random (MAR) mechanism with theoretical support. |
Zongyu Dai; Zhiqi Bu; Qi Long; | arxiv-cs.LG | 2021-12-21 |
| 57 | Adversarial Neural Networks for Error Correcting Codes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a general framework to further boost the performance and applicability of ML models. |
Hung T. Nguyen; Steven Bottone; Kwang Taik Kim; Mung Chiang; H. Vincent Poor; | arxiv-cs.LG | 2021-12-21 |
| 58 | A Theoretical View of Linear Backpropagation and Its Convergence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper serves as a complement and somewhat an extension to Guo et al.’s paper, by providing theoretical analyses on LinBP in neural-network-involved learning tasks including adversarial attack and model training. |
Ziang Li; Yiwen Guo; Haodi Liu; Changshui Zhang; | arxiv-cs.LG | 2021-12-21 |
| 59 | Turbo-Sim: A Generalised Generative Model with A Physical Latent Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Turbo-Sim, a generalised autoencoder framework derived from principles of information theory that can be used as a generative model. |
Guillaume Quétant; Mariia Drozdova; Vitaliy Kinakh; Tobias Golling; Slava Voloshynovskiy; | arxiv-cs.LG | 2021-12-20 |
| 60 | Multimodal Adversarially Learned Inference with Factorized Discriminators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel approach to generative modeling of multimodal data based on generative adversarial networks. |
Wenxue Chen; Jianke Zhu; | arxiv-cs.LG | 2021-12-20 |
| 61 | Evaluation and Comparison of Deep Learning Methods for Pavement Crack Identification with Visual Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the aspect of patch sample classification, the fine-tuned TL models can be equivalent to or even slightly better than the ED models in accuracy, and the predicting time is faster; In the aspect of accurate crack location, both ED and GAN algorithms can achieve pixel-level segmentation and is expected to be detected in real time on low computing power platform. |
Kai-Liang Lu; | arxiv-cs.CV | 2021-12-20 |
| 62 | 3D-aware Image Synthesis Via Learning Structural and Textural Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate these two problems, we propose a novel framework, termed as VolumeGAN, for high-fidelity 3D-aware image synthesis, through explicitly learning a structural representation and a textural representation. |
Yinghao Xu; Sida Peng; Ceyuan Yang; Yujun Shen; Bolei Zhou; | arxiv-cs.CV | 2021-12-20 |
| 63 | StyleSwin: Transformer-based GAN for High-resolution Image Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we seek to explore using pure transformers to build a generative adversarial network for high-resolution image synthesis. |
BOWEN ZHANG et. al. | arxiv-cs.CV | 2021-12-20 |
| 64 | Initiative Defense Against Facial Manipulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the limitation, in this paper, we propose a novel framework of initiative defense to degrade the performance of facial manipulation models controlled by malicious users. |
Qidong Huang; Jie Zhang; Wenbo Zhou; WeimingZhang; Nenghai Yu; | arxiv-cs.CV | 2021-12-19 |
| 65 | FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a framework, FedNI, to leverage network inpainting and inter-institutional data via FL. |
Liang Peng; Nan Wang; Nicha Dvornek; Xiaofeng Zhu; Xiaoxiao Li; | arxiv-cs.LG | 2021-12-19 |
| 66 | Investigation of Densely Connected Convolutional Networks with Domain Adversarial Learning for Noise Robust Speech Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate densely connected convolutional networks (DenseNets) and their extension with domain adversarial training for noise robust speech recognition. |
Chia Yu Li; Ngoc Thang Vu; | arxiv-cs.CL | 2021-12-19 |
| 67 | Generation of Data on Discontinuous Manifolds Via Continuous Stochastic Non-invertible Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, instead of trying to keep the latent space to be Gaussian, we use a pre-trained contrastive encoder to obtain a clustered latent space. |
Mariia Drozdova; Vitaliy Kinakh; Guillaume Quétant; Tobias Golling; Slava Voloshynovskiy; | arxiv-cs.LG | 2021-12-17 |
| 68 | Information-theoretic Stochastic Contrastive Conditional GAN: InfoSCC-GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a stochastic contrastive conditional generative adversarial network (InfoSCC-GAN) with an explorable latent space. |
Vitaliy Kinakh; Mariia Drozdova; Guillaume Quétant; Tobias Golling; Slava Voloshynovskiy; | arxiv-cs.CV | 2021-12-17 |
| 69 | NFTGAN: Non-Fungible Token Art Generation Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a GAN-based architecture is implemented and evaluated for novel NFT-style digital arts generation. |
Sakib Shahriar; Kadhim Hayawi; | arxiv-cs.LG | 2021-12-17 |
| 70 | Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the dynamics-aware adversarial attack problem in deep neural networks. |
AN TAO et. al. | arxiv-cs.CV | 2021-12-17 |
| 71 | Towards Robust Real-time Audio-Visual Speech Enhancement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel framework for low latency speaker-independent AV SE that can generalise on a range of visual and acoustic noises. |
Mandar Gogate; Kia Dashtipour; Amir Hussain; | arxiv-cs.SD | 2021-12-16 |
| 72 | An Unsupervised Way to Understand Artifact Generating Internal Units in Generative Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose the concept of local activation, and devise a metric on the local activation to detect artifact generations without additional supervision. |
Haedong Jeong; Jiyeon Han; Jaesik Choi; | arxiv-cs.CV | 2021-12-16 |
| 73 | Imbalanced Sample Generation and Evaluation for Power System Transient Stability Using CTGAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a controllable sample generation framework based on Conditional Tabular Generative Adversarial Network (CTGAN) to generate specified transient stability samples. |
GENGSHI HAN et. al. | arxiv-cs.LG | 2021-12-16 |
| 74 | Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Later, we apply the iterative adversarial finetuning to refine pretrained models. |
Tong Chen; Zhan Ma; | arxiv-cs.CV | 2021-12-16 |
| 75 | Models in The Loop: Aiding Crowdworkers with Generative Annotation Assistants Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we examine if we can maintain the advantages of DADC, without suffering the additional cost. |
MAX BARTOLO et. al. | arxiv-cs.CL | 2021-12-16 |
| 76 | Addressing Adversarial Machine Learning Attacks in Smart Healthcare Perspectives Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address the type of adversarial attacks and their impact on smart healthcare systems. |
Arawinkumaar Selvakkumar; Shantanu Pal; Zahra Jadidi; | arxiv-cs.DC | 2021-12-16 |
| 77 | A Robust Optimization Approach to Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new, more principled approach to adversarial training based on a closed form solution of an upper bound of the adversarial loss, which can be effectively trained with backpropagation. |
Dimitris Bertsimas; Xavier Boix; Kimberly Villalobos Carballo; Dick den Hertog; | arxiv-cs.LG | 2021-12-16 |
| 78 | All You Need Is RAW: Defending Against Adversarial Attacks with Camera Image Pipelines Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we proposed a model-agnostic adversarial defensive method, which maps the input RGB images to Bayer RAW space and back to output RGB using a learned camera image signal processing (ISP) pipeline to eliminate potential adversarial patterns. |
Yuxuan Zhang; Bo Dong; Felix Heide; | arxiv-cs.CV | 2021-12-16 |
| 79 | High Fidelity Visualization of What Your Self-Supervised Representation Knows About Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we showcase the use of a conditional diffusion based generative model (RCDM) to visualize representations learned with self-supervised models. |
Florian Bordes; Randall Balestriero; Pascal Vincent; | arxiv-cs.LG | 2021-12-16 |
| 80 | Leveraging Image-based Generative Adversarial Networks for Time Series Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The paper proposes the intertemporal return plot (IRP) representation to facilitate the use of image-based generative adversarial networks for time series generation. |
Justin Hellermann; Stefan Lessmann; | arxiv-cs.LG | 2021-12-15 |
| 81 | Efficient Geometry-aware 3D Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we improve the computational efficiency and image quality of 3D GANs without overly relying on these approximations. |
ERIC R. CHAN et. al. | arxiv-cs.CV | 2021-12-15 |
| 82 | Self-Ensembling GAN for Cross-Domain Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate the annotation burden, this paper proposes a self-ensembling generative adversarial network (SE-GAN) exploiting cross-domain data for semantic segmentation. |
Yonghao Xu; Fengxiang He; Bo Du; Liangpei Zhang; Dacheng Tao; | arxiv-cs.CV | 2021-12-15 |
| 83 | On The Convergence and Robustness of Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose such a criterion, namely First-Order Stationary Condition for constrained optimization (FOSC), to quantitatively evaluate the convergence quality of adversarial examples found in the inner maximization. |
YISEN WANG et. al. | arxiv-cs.LG | 2021-12-15 |
| 84 | Tackling The Generative Learning Trilemma with Denoising Diffusion GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that slow sampling in these models is fundamentally attributed to the Gaussian assumption in the denoising step which is justified only for small step sizes. |
Zhisheng Xiao; Karsten Kreis; Arash Vahdat; | arxiv-cs.LG | 2021-12-14 |
| 85 | GM Score: Incorporating Inter-class and Intra-class Generator Diversity, Discriminability of Disentangled Representation, and Sample Fidelity for Evaluating GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new score, namely, GM Score, which takes into various factors such as sample quality, disentangled representation, intra-class and inter-class diversity, and other metrics such as precision, recall, and F1 score are employed for discriminability of latent space of deep belief network (DBN) and restricted Boltzmann machine (RBM). |
Harshvardhan GM; Aanchal Sahu; Mahendra Kumar Gourisaria; | arxiv-cs.LG | 2021-12-13 |
| 86 | DGL-GAN: Discriminator Guided Learning for GAN Compression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel yet simple {\bf D}iscriminator {\bf G}uided {\bf L}earning approach for compressing vanilla {\bf GAN}, dubbed {\bf DGL-GAN}. |
Yuesong Tian; Li Shen; Dacheng Tao; Zhifeng Li; Wei Liu; | arxiv-cs.CV | 2021-12-13 |
| 87 | MAGIC: Multimodal RelAtional Graph AdversarIal InferenCe for Diverse and Unpaired Text-based Image Captioning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the Multimodal relAtional Graph adversarIal inferenCe (MAGIC) framework for diverse and unpaired TextCap. |
WENQIAO ZHANG et. al. | arxiv-cs.CV | 2021-12-13 |
| 88 | Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this issue, we propose the Robust Mixup strategy in which we maximize the adversity of the interpolated images and gain robustness and prevent overfitting. |
CHUN PONG LAU et. al. | arxiv-cs.CV | 2021-12-12 |
| 89 | MedAttacker: Exploring Black-Box Adversarial Attacks on Risk Prediction Models in Healthcare Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To fill this gap, we propose the first black-box adversarial attack method against health risk prediction models named MedAttacker to investigate their vulnerability. |
MUCHAO YE et. al. | arxiv-cs.LG | 2021-12-11 |
| 90 | Faster Single-loop Algorithms for Minimax Optimization Without Strong Concavity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Albeit its desirable simplicity, recent work shows inferior convergence rates of GDA in theory even assuming strong concavity of the objective on one side. |
Junchi Yang; Antonio Orvieto; Aurelien Lucchi; Niao He; | arxiv-cs.LG | 2021-12-10 |
| 91 | Preemptive Image Robustification for Protecting Users Against Man-in-the-Middle Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on a real-world threat model where a Man-in-the-Middle adversary maliciously intercepts and perturbs images web users upload online. |
Seungyong Moon; Gaon An; Hyun Oh Song; | arxiv-cs.LG | 2021-12-10 |
| 92 | SmartCon: Deep Probabilistic Learning Based Intelligent Link-Configuration in Narrowband-IoT Towards 5G and B5G Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Accordingly, in this paper, we propose SmartCon which is a Generative Adversarial Network (GAN)-based deep learning approach for auto link-configuration during uplink or downlink scheduling, such that the packet loss rate is significantly reduced in NB-IoT networks. |
Raja Karmakar; Georges Kaddoum; Samiran Chattopadhyay; | arxiv-cs.NI | 2021-12-09 |
| 93 | Uncertainty, Edge, and Reverse-Attention Guided Generative Adversarial Network for Automatic Building Detection in Remotely Sensed Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these problems, we propose a generative adversarial network based segmentation framework with uncertainty attention unit and refinement module embedded in the generator. |
Somrita Chattopadhyay; Avinash C. Kak; | arxiv-cs.CV | 2021-12-09 |
| 94 | Multimodal Conditional Image Synthesis with Product-of-Experts GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this limitation, we propose the Product-of-Experts Generative Adversarial Networks (PoE-GAN) framework, which can synthesize images conditioned on multiple input modalities or any subset of them, even the empty set. |
Xun Huang; Arun Mallya; Ting-Chun Wang; Ming-Yu Liu; | arxiv-cs.CV | 2021-12-09 |
| 95 | A Shared Representation for Photorealistic Driving Simulators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to improve the quality of generated images by rethinking the discriminator architecture. |
Saeed Saadatnejad; Siyuan Li; Taylor Mordan; Alexandre Alahi; | arxiv-cs.CV | 2021-12-09 |
| 96 | Robustness Certificates for Implicit Neural Networks: A Mixed Monotone Contractive Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a theoretical and computational framework for robustness verification of implicit neural networks; our framework blends together mixed monotone systems theory and contraction theory. |
Saber Jafarpour; Matthew Abate; Alexander Davydov; Francesco Bullo; Samuel Coogan; | arxiv-cs.LG | 2021-12-09 |
| 97 | Mutual Adversarial Training: Learning Together Is Better Than Going Alone Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study how interactions among models affect robustness via knowledge distillation. |
Jiang Liu; Chun Pong Lau; Hossein Souri; Soheil Feizi; Rama Chellappa; | arxiv-cs.LG | 2021-12-09 |
| 98 | PARL: Enhancing Diversity of Ensemble Networks to Resist Adversarial Attacks Via Pairwise Adversarially Robust Loss Function Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present extensive experiments using standard image classification datasets like CIFAR-10 and CIFAR-100 trained using standard ResNet20 classifier against state-of-the-art adversarial attacks to demonstrate the robustness of the proposed ensemble methodology. |
Manaar Alam; Shubhajit Datta; Debdeep Mukhopadhyay; Arijit Mondal; Partha Pratim Chakrabarti; | arxiv-cs.LG | 2021-12-09 |
| 99 | RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The attack method we propose, RamBoAttack, exploits the notion of Randomized Block Coordinate Descent to explore the hidden classifier manifold, targeting perturbations to manipulate only localized input features to address the issues of gradient estimation methods. |
Viet Quoc Vo; Ehsan Abbasnejad; Damith C. Ranasinghe; | arxiv-cs.LG | 2021-12-09 |
| 100 | Multiple Residual Dense Networks for Reconfigurable Intelligent Surfaces Cascaded Channel Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Reconfigurable intelligent surface (RIS) constitutes an essential and promising paradigm that relies programmable wireless environment and provides capability for space-intensive … |
YU JIN et. al. | arxiv-cs.IT | 2021-12-08 |
| 101 | Feature Statistics Mixing Regularization for Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a remedy, we propose feature statistics mixing regularization (FSMR) that encourages the discriminator’s prediction to be invariant to the styles of input images. |
Junho Kim; Yunjey Choi; Youngjung Uh; | arxiv-cs.CV | 2021-12-08 |
| 102 | Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a novel GAN model, i.e., AU-GAN, which has an asymmetric architecture for adverse domain translation. |
JEONG-GI KWAK et. al. | arxiv-cs.CV | 2021-12-08 |
| 103 | A Unified Architecture of Semantic Segmentation and Hierarchical Generative Adversarial Networks for Expression Manipulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To demonstrate its advantages, we evaluate our method on two challenging facial expression translation benchmarks, AffectNet and RaFD, and a semantic segmentation benchmark, CelebAMask-HQ across two popular architectures, BiSeNet and UNet. |
Rumeysa Bodur; Binod Bhattarai; Tae-Kyun Kim; | arxiv-cs.CV | 2021-12-08 |
| 104 | On Visual Self-supervision and Its Effect on Model Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We identify primary ways in which self-supervision can be added to adversarial training, and observe that using a self-supervised loss to optimize both network parameters and find adversarial examples leads to the strongest improvement in model robustness, as this can be viewed as a form of ensemble adversarial training. |
Michal Kucer; Diane Oyen; Garrett Kenyon; | arxiv-cs.CV | 2021-12-08 |
| 105 | SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper therefore aims to comprehensively investigate the adversarial robustness of NLVL models by examining three facets of vulnerabilities from both attack and defense aspects. |
WENBO GOU et. al. | arxiv-cs.CV | 2021-12-08 |
| 106 | Permutation Equivariant Generative Adversarial Networks for Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: After having discussed some properties of such functions, we propose 3G-GAN, a 3-stages model relying on GANs and equivariant functions. |
Yoann Boget; Magda Gregorova; Alexandros Kalousis; | arxiv-cs.LG | 2021-12-07 |
| 107 | Generative Adversarial Networks for Labeled Data Creation for Structural Monitoring and Damage Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Structural Health Monitoring (SHM) is one of those fields that use Artificial Intelligence (AI) such as Machine Learning (ML) and Deep Learning (DL) algorithms for condition assessment of civil structures based on the collected data. |
Furkan Luleci; F. Necati Catbas; Onur Avci; | arxiv-cs.LG | 2021-12-06 |
| 108 | Adversarial Machine Learning In Network Intrusion Detection Domain: A Systematic Review Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Due to their massive success in various domains, deep learning techniques are increasingly used to design network intrusion detection solutions that detect and mitigate unknown and known attacks with high accuracy detection rates and minimal feature engineering. |
Huda Ali Alatwi; Charles Morisset; | arxiv-cs.CR | 2021-12-06 |
| 109 | BDFA: A Blind Data Adversarial Bit-flip Attack on Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Blind Data Adversarial Bit-flip Attack (BDFA), a novel technique to enable BFA without any access to the training or testing data. |
Behnam Ghavami; Mani Sadati; Mohammad Shahidzadeh; Zhenman Fang; Lesley Shannon; | arxiv-cs.CR | 2021-12-06 |
| 110 | Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work explores the potency of stochastic competition-based activations, namely Stochastic Local Winner-Takes-All (LWTA), against powerful (gradient-based) white-box and black-box adversarial attacks; we especially focus on Adversarial Training settings. |
Konstantinos P. Panousis; Sotirios Chatzis; Sergios Theodoridis; | arxiv-cs.LG | 2021-12-05 |
| 111 | Implicit Data Augmentation Using Feature Interpolation for Diversified Low-Shot Image Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate this issue, we propose a novel implicit data augmentation approach which facilitates stable training and synthesize diverse samples. |
Mengyu Dai; Haibin Hang; Xiaoyang Guo; | arxiv-cs.CV | 2021-12-04 |
| 112 | Construct Informative Triplet with Two-stage Hard-sample Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a robust sample generation scheme to construct informative triplets. |
CHUANG ZHU et. al. | arxiv-cs.CV | 2021-12-04 |
| 113 | PreGAN: Preemptive Migration Prediction Network for Proactive Fault-Tolerant Edge Computing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose PreGAN, a composite AI model using a Generative Adversarial Network (GAN) to predict preemptive migration decisions for proactive fault-tolerance in containerized edge deployments. |
Shreshth Tuli; Giuliano Casale; Nicholas R. Jennings; | arxiv-cs.DC | 2021-12-04 |
| 114 | Music-to-Dance Generation with Optimal Transport IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Music-to-Dance with Optimal Transport Network (MDOT-Net) for learning to generate 3D dance choreographs from music. |
Shuang Wu; Shijian Lu; Li Cheng; | arxiv-cs.SD | 2021-12-03 |
| 115 | Generative Adversarial Networks for Synthetic Data Generation: A Comparative Study IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we consider the potential application of GANs for the purpose of generating synthetic census microdata. |
Claire Little; Mark Elliot; Richard Allmendinger; Sahel Shariati Samani; | arxiv-cs.LG | 2021-12-03 |
| 116 | Semantic Map Injected GAN Training for Image-to-Image Translation IF:5 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we perform the semantic injected training of GAN models. |
BALARAM SINGH KSHATRIYA et. al. | arxiv-cs.CV | 2021-12-03 |
| 117 | Blackbox Untargeted Adversarial Testing of Automatic Speech Recognition Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To help test the correctness of ASRS, we propose techniques that automatically generate blackbox (agnostic to the DNN), untargeted adversarial attacks that are portable across ASRs. |
Xiaoliang Wu; Ajitha Rajan; | arxiv-cs.SD | 2021-12-03 |
| 118 | Adversarial Attacks Against A Satellite-borne Multispectral Cloud Detector IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we highlight the vulnerability of deep learning-based cloud detection towards adversarial attacks. |
ANDREW DU et. al. | arxiv-cs.CV | 2021-12-03 |
| 119 | Single-Shot Black-Box Adversarial Attacks Against Malware Detectors: A Causal Language Model Approach IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we show that a novel DL-based causal language model enables single-shot evasion (i.e., with only one query to malware detector) by treating the content of the malware executable as a byte sequence and training a Generative Pre-Trained Transformer (GPT). |
James Lee Hu; Mohammadreza Ebrahimi; Hsinchun Chen; | arxiv-cs.CR | 2021-12-03 |
| 120 | Altering Facial Expression Based on Textual Emotion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to change the facial expression in an image using GAN, where the input image with an initial expression (i.e., happy) is altered to a different expression (i.e., disgusted) for the same person. |
MOHAMMAD IMRUL JUBAIR et. al. | arxiv-cs.CV | 2021-12-02 |
| 121 | Is Approximation Universally Defensive Against Adversarial Attacks in Deep Neural Networks? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards this, we present an extensive adversarial robustness analysis of different approximate DNN accelerators (AxDNNs) using the state-of-the-art approximate multipliers. |
Ayesha Siddique; Khaza Anuarul Hoque; | arxiv-cs.LG | 2021-12-02 |
| 122 | CYBORG: Blending Human Saliency Into The Loss Improves Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: All data, code and pre-trained models used in this work are offered with this paper. |
Aidan Boyd; Patrick Tinsley; Kevin Bowyer; Adam Czajka; | arxiv-cs.CV | 2021-12-01 |
| 123 | FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present FaceTuneGAN, a new 3D face model representation decomposing and encoding separately facial identity and facial expression. |
Nicolas Olivier; Kelian Baert; Fabien Danieau; Franck Multon; Quentin Avril; | arxiv-cs.CV | 2021-12-01 |
| 124 | Improving GAN Equilibrium By Raising Spatial Awareness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate the issue of D dominating the competition in GANs, we aim to raise the spatial awareness of G. Randomly sampled multi-level heatmaps are encoded into the intermediate layers of G as an inductive bias. |
JIANYUAN WANG et. al. | arxiv-cs.CV | 2021-12-01 |
| 125 | $\ell_\infty$-Robustness and Beyond: Unleashing Efficient Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, by leveraging the theory of coreset selection we show how selecting a small subset of training data provides a more principled approach towards reducing the time complexity of robust training. |
Hadi M. Dolatabadi; Sarah Erfani; Christopher Leckie; | arxiv-cs.LG | 2021-12-01 |
| 126 | Robustness in Deep Learning for Computer Vision: Mind The Gap? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To provide a more transparent definition of robustness across contexts, we introduce a structural causal model of the data generating process and interpret non-adversarial robustness as pertaining to a model’s behavior on corrupted images which correspond to low-probability samples from the unaltered data distribution. |
Nathan Drenkow; Numair Sani; Ilya Shpitser; Mathias Unberath; | arxiv-cs.CV | 2021-12-01 |
| 127 | Generative Convolution Layer for Image Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a novel convolution method, called generative convolution (GConv), which is simple yet effective for improving the generative adversarial network (GAN) performance. |
Seung Park; Yong-Goo Shin; | arxiv-cs.CV | 2021-11-30 |
| 128 | Improvement in Machine Translation with Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore machine translation improvement via Generative Adversarial Network (GAN) architecture. |
Jay Ahn; Hari Madhu; Viet Nguyen; | arxiv-cs.CL | 2021-11-30 |
| 129 | Using A GAN to Generate Adversarial Examples to Facial Image Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we use a Generative Adversarial Network (GAN) to create adversarial examples to deceive facial recognition and we achieve an acceptable success rate in fooling the face recognition. |
Andrew Merrigan; Alan F. Smeaton; | arxiv-cs.CV | 2021-11-30 |
| 130 | FMD-cGAN: Fast Motion Deblurring Using Conditional Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a Fast Motion Deblurring-Conditional Generative Adversarial Network (FMD-cGAN) that helps in blind motion deblurring of a single image. |
Jatin Kumar; Indra Deep Mastan; Shanmuganathan Raman; | arxiv-cs.CV | 2021-11-30 |
| 131 | Adversarial Attacks Against Deep Generative Models on Data: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For each model, component and attack, we review the current research progress and identify the key challenges. |
Hui Sun; Tianqing Zhu; Zhiqiu Zhang; Dawei Jin. Ping Xiong; Wanlei Zhou; | arxiv-cs.CR | 2021-11-30 |
| 132 | Leveraging Intrinsic Gradient Information for Further Training of Differentiable Machine Learning Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents methods demonstrating that when the derivatives of target variables (outputs) with respect to inputs can be extracted from processes of interest, e.g., neural networks (NN) based surrogate models, they can be leveraged to further improve the accuracy of differentiable ML models. |
Chris McDonagh; Xi Chen; | arxiv-cs.LG | 2021-11-30 |
| 133 | Molecular Attributes Transfer from Non-Parallel Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, for the first time, we formulate molecular optimization as a style transfer problem and present a novel generative model that could automatically learn internal differences between two groups of non-parallel data through adversarial training strategies. |
SHUANGJIA ZHENG et. al. | arxiv-cs.LG | 2021-11-30 |
| 134 | FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address such limitations, we propose the Few-shot ROBust (FROB) model for classification and few-shot OoD detection. |
Nikolaos Dionelis; | arxiv-cs.LG | 2021-11-30 |
| 135 | Continuous Conditional Generative Adversarial Networks for Data-driven Solutions of Poroelasticity with Heterogeneous Material Properties Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, our previous approach of conditional generative adversarial networks (cGAN) developed for steady-state problems with heterogeneous materials is extended to time-dependent problems by adopting the concept of continuous cGAN (CcGAN). |
T. KADEETHUM et. al. | arxiv-cs.CE | 2021-11-29 |
| 136 | Generative Adversarial Networks with Conditional Neural Movement Primitives for An Interactive Generative Drawing Tool Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we proposed a new framework, Generative Adversarial Networks with Conditional Neural Movement Primitives (GAN-CNMP), that incorporates a novel adversarial loss on CNMP to increase sketch smoothness and consistency. |
Suzan Ece Ada; M. Yunus Seker; | arxiv-cs.GR | 2021-11-29 |
| 137 | Weakly-supervised Generative Adversarial Networks for Medical Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel medical image classification algorithm, called Weakly-Supervised Generative Adversarial Networks (WSGAN), which only uses a small number of real images without labels to generate fake images or mask images to enlarge the sample size of the training set. |
Jiawei Mao; Xuesong Yin; Yuanqi Chang; Qi Huang; | arxiv-cs.CV | 2021-11-29 |
| 138 | Energy-Efficient Implementation of Generative Adversarial Networks on Passive RRAM Crossbar Arrays Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we have proposed an implementation of GANs on passive memristor crossbar arrays. |
Siddharth Satyam; Honey Nikam; Shubham Sahay; | arxiv-cs.ET | 2021-11-29 |
| 139 | EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate the instability issue, we propose an efficient two-stage evolutionary algorithm (EA) based NAS framework to discover GANs, dubbed \textbf{EAGAN}. |
Guohao Ying; Xin He; Bin Gao; Bo Han; Xiaowen Chu; | arxiv-cs.CV | 2021-11-29 |
| 140 | On Predicting Generalization Using GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Research on generalization bounds for deep networks seeks to give ways to predict test error using just the training dataset and the network parameters. |
Yi Zhang; Arushi Gupta; Nikunj Saunshi; Sanjeev Arora; | arxiv-cs.LG | 2021-11-28 |
| 141 | Adaptive Perturbation for Adversarial Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to remove the sign function and directly utilize the exact gradient direction with a scaling factor for generating adversarial perturbations, which improves the attack success rates of adversarial examples even with fewer perturbations. |
Zheng Yuan; Jie Zhang; Shiguang Shan; | arxiv-cs.CV | 2021-11-27 |
| 142 | Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The mode collapse problem is introduced and various methods, including minibatch GAN, unrolled GAN, BourGAN, mixture GAN, D2GAN, and Wasserstein GAN, are introduced for resolving this problem. |
Benyamin Ghojogh; Ali Ghodsi; Fakhri Karray; Mark Crowley; | arxiv-cs.LG | 2021-11-25 |
| 143 | Joint Inference and Input Optimization in Equilibrium Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that there is a natural synergy between these two settings. |
Swaminathan Gurumurthy; Shaojie Bai; Zachary Manchester; J. Zico Kolter; | arxiv-cs.LG | 2021-11-25 |
| 144 | AdvBokeh: Learning to Adversarially Defocus Blur Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To further improve the realisticity of the adversarial bokeh, we propose depth-guided gradient-based attack to regularize the gradient.We validate the proposed method on a popular adversarial image classification dataset, i.e., NeurIPS-2017 DEV, and show that the proposed method can penetrate four state-of-the-art (SOTA) image classification networks i.e., ResNet50, VGG, DenseNet, and MobileNetV2 with a high success rate as well as high image quality. |
YIHAO HUANG et. al. | arxiv-cs.CV | 2021-11-25 |
| 145 | Clustering Effect of (Linearized) Adversarial Robust Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we interpret adversarial robustness from the perspective of linear components, and find that there exist some statistical properties for comprehensively robust models. |
Yang Bai; Xin Yan; Yong Jiang; Shu-Tao Xia; Yisen Wang; | arxiv-cs.LG | 2021-11-25 |
| 146 | Optimizing Latent Space Directions For GAN-based Local Image Editing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We thus present a novel objective function to evaluate the locality of an image edit. |
Ehsan Pajouheshgar; Tong Zhang; Sabine Süsstrunk; | arxiv-cs.CV | 2021-11-24 |
| 147 | A Method for Evaluating The Capacity of Generative Adversarial Networks to Reproduce High-order Spatial Context Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate several tests of the statistical accuracy of images output by two popular GAN architectures. |
Rucha Deshpande; Mark A. Anastasio; Frank J. Brooks; | arxiv-cs.CV | 2021-11-24 |
| 148 | LDDMM Meets GANs: Generative Adversarial Networks for Diffeomorphic Registration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The purpose of this work is to contribute to the state of the art of deep-learning methods for diffeomorphic registration. |
Ubaldo Ramon; Monica Hernandez; Elvira Mayordomo; | arxiv-cs.CV | 2021-11-24 |
| 149 | Thundernna: A White Box Adversarial Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In This project, we develop a first-order method to attack the neural network. |
Linfeng Ye; | arxiv-cs.LG | 2021-11-24 |
| 150 | Robustness Against Adversarial Attacks in Neural Networks Using Incremental Dissipativity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes an incremental dissipativity-based robustness certificate for neural networks in the form of a linear matrix inequality for each layer. |
Bernardo Aquino; Arash Rahnama; Peter Seiler; Lizhen Lin; Vijay Gupta; | arxiv-cs.LG | 2021-11-24 |
| 151 | EAD: An Ensemble Approach to Detect Adversarial Examples from The Hidden Features of Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a novel approach named Ensemble Adversarial Detector (EAD) for the identification of adversarial examples, in a standard multiclass classification scenario. |
FRANCESCO CRAIGHERO et. al. | arxiv-cs.CV | 2021-11-24 |
| 152 | Challenges of Adversarial Image Augmentations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that random augmentations are still competitive compared to an optimal adversarial approach, as well as to simple curricula, and conjecture that the success of AdvAA is due to the stochasticity of the policy controller network, which introduces a mild form of curriculum. |
Arno Blaas; Xavier Suau; Jason Ramapuram; Nicholas Apostoloff; Luca Zappella; | arxiv-cs.LG | 2021-11-24 |
| 153 | Three-Way Deep Neural Network for Radio Frequency Map Generation and Source Localization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a Generative Adversarial Network (GAN) machine learning model to interpolate irregularly distributed measurements across the spatial domain to construct a smooth radio frequency map (RFMap) and then perform localization using a deep neural network. |
Kuldeep S. Gill; Son Nguyen; Myo M. Thein; Alexander M. Wyglinski; | arxiv-cs.LG | 2021-11-23 |
| 154 | Distribution Estimation to Automate Transformation Policies for Self-Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Building on this observation, we propose a framework based on generative adversarial network to automatically find the transformations which are not present in the input dataset and thus effective for the self-supervised learning. |
Seunghan Yang; Debasmit Das; Simyung Chang; Sungrack Yun; Fatih Porikli; | arxiv-cs.CV | 2021-11-23 |
| 155 | Generative Adversarial Networks for Astronomical Images Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this research, using a Lightweight GAN, a dataset of images obtained from the web, and the Galaxy Zoo Dataset, we have generated thousands of new images of celestial bodies, galaxies, and finally, by combining them, a wide view of the universe. |
Davide Coccomini; Nicola Messina; Claudio Gennaro; Fabrizio Falchi; | arxiv-cs.CV | 2021-11-22 |
| 156 | Adversarial Examples on Segmentation Models Can Be Easy to Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we intensively study this topic. |
Jindong Gu; Hengshuang Zhao; Volker Tresp; Philip Torr; | arxiv-cs.CV | 2021-11-22 |
| 157 | Local Linearity and Double Descent in Catastrophic Overfitting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: $ Further, inspired by Parseval networks, we introduce a regularization term to AT with FGSM to make the weight matrices of the network orthogonal and study the connection between orthogonality of the network weights and local linearity. |
Varun Sivashankar; Nikil Selvam; | arxiv-cs.LG | 2021-11-21 |
| 158 | Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting The Adversarial Transferability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we treat the iterative ensemble attack as a stochastic gradient descent optimization process, in which the variance of the gradients on different models may lead to poor local optima. |
Yifeng Xiong; Jiadong Lin; Min Zhang; John E. Hopcroft; Kun He; | arxiv-cs.LG | 2021-11-21 |
| 159 | Medical Aegis: Robust Adversarial Protectors for Medical Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel adversarial example defense system called Medical Aegis. |
Qingsong Yao; Zecheng He; S. Kevin Zhou; | arxiv-cs.CV | 2021-11-21 |
| 160 | Denoised Internal Models: A Brain-Inspired Autoencoder Against Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by recent advances in brain science, we propose the Denoised Internal Models (DIM), a novel generative autoencoder-based model to tackle this challenge. |
KAIYUAN LIU et. al. | arxiv-cs.CV | 2021-11-21 |
| 161 | Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To measure the difference between two probability distributions, referred to as the source and target, respectively, we exploit both the chain rule and Bayes’ theorem to construct conditional transport (CT), which is constituted by both a forward component and a backward one. |
Huangjie Zheng; Mingyuan Zhou; | nips | 2021-11-20 |
| 162 | Improved Transformer for High-Resolution GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce two key ingredients to Transformer to address this challenge. |
Long Zhao; Zizhao Zhang; Ting Chen; Dimitris Metaxas; Han Zhang; | nips | 2021-11-20 |
| 163 | Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce two cures for ACGAN. |
Minguk Kang; Woohyeon Shim; Minsu Cho; Jaesik Park; | nips | 2021-11-20 |
| 164 | CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. |
Sakshi Varshney; Vinay Kumar Verma; P. K. Srijith; Lawrence Carin; Piyush Rai; | nips | 2021-11-20 |
| 165 | Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Built upon EG+ and EAG, this paper proposes a two-time-scale EG with anchoring, named fast extragradient (FEG), that has a fast $\mathcal{O}(1/k^2)$ rate on the squared gradient norm for smooth structured nonconvex-nonconcave problems; the corresponding saddle-gradient operator satisfies the negative comonotonicity condition. |
Sucheol Lee; Donghwan Kim; | nips | 2021-11-20 |
| 166 | Alias-Free Generative Adversarial Networks IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Interpreting all signals in the network as continuous, we derive generally applicable, small architectural changes that guarantee that unwanted information cannot leak into the hierarchical synthesis process. |
TERO KARRAS et. al. | nips | 2021-11-20 |
| 167 | Lip to Speech Synthesis with Visual Context Attentional GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel lip-to-speech generative adversarial network, Visual Context Attentional GAN (VCA-GAN), which can jointly model local and global lip movements during speech synthesis. |
Minsu Kim; Joanna Hong; Yong Man Ro; | nips | 2021-11-20 |
| 168 | Unsupervised Noise Adaptive Speech Enhancement By Discriminator-Constrained Optimal Transport Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel discriminator-constrained optimal transport network (DOTN) that performs unsupervised domain adaptation for speech enhancement (SE), which is an essential regression task in speech processing. |
Hsin-Yi Lin; Huan-Hsin Tseng; Xugang Lu; Yu Tsao; | nips | 2021-11-20 |
| 169 | Time-series Generation By Contrastive Imitation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy, where the reinforcement signal is provided by a global (but stepwise-decomposable) energy model trained by contrastive estimation. |
Daniel Jarrett; Ioana Bica; Mihaela van der Schaar; | nips | 2021-11-20 |
| 170 | The Image Local Autoregressive Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these limitations, we propose a novel model — image Local Autoregressive Transformer (iLAT), to better facilitate the locally guided image synthesis. |
CHENJIE CAO et. al. | nips | 2021-11-20 |
| 171 | Training for The Future: A Simple Gradient Interpolation Loss to Generalize Along Time Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Responding to the above limitations, we propose a simple method that starts with a model with time-sensitive parameters but regularizes its temporal complexity using a Gradient Interpolation (GI) loss. |
Anshul Nasery; Soumyadeep Thakur; Vihari Piratla; Abir De; Sunita Sarawagi; | nips | 2021-11-20 |
| 172 | Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To promote diversity in sample generation without degrading the overall quality, we propose a simple yet effective method to diagnose and emphasize underrepresented samples during training of a GAN. |
Jinhee Lee; Haeri Kim; Youngkyu Hong; Hye Won Chung; | nips | 2021-11-20 |
| 173 | Statistical Regeneration Guarantees of The Wasserstein Autoencoder with Latent Space Consistency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To close this gap, in this paper, we investigate the statistical properties of WAE. |
Anish Chakrabarty; Swagatam Das; | nips | 2021-11-20 |
| 174 | Bounds All Around: Training Energy-based Models with Bidirectional Bounds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a bidirectional bound on the EBM log-likelihood, such that we maximize a lower bound and minimize an upper bound when solving the minimax game. |
Cong Geng; Jia Wang; Zhiyong Gao; Jes Frellsen; S�ren Hauberg; | nips | 2021-11-20 |
| 175 | Modified Frank Wolfe in Probability Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel Frank-Wolfe (FW) procedure for the optimization of infinite-dimensional functionals of probability measures – a task which arises naturally in a wide range of areas including statistical learning (e.g. variational inference) and artificial intelligence (e.g. generative adversarial networks). |
Carson Kent; Jiajin Li; Jose Blanchet; Peter W. Glynn; | nips | 2021-11-20 |
| 176 | AGA-GAN: Attribute Guided Attention Generative Adversarial Network with U-Net for Face Hallucination Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an Attribute Guided Attention Generative Adversarial Network which employs novel attribute guided attention (AGA) modules to identify and focus the generation process on various facial features in the image. |
Abhishek Srivastava; Sukalpa Chanda; Umapada Pal; | arxiv-cs.CV | 2021-11-20 |
| 177 | Domain Invariant Representation Learning with Domain Density Transformations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a theoretically grounded method to learn a domain-invariant representation by enforcing the representation network to be invariant under all transformation functions among domains. |
A. Tuan Nguyen; Toan Tran; Yarin Gal; Atilim Gunes Baydin; | nips | 2021-11-20 |
| 178 | Instance-Conditioned GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take inspiration from kernel density estimation techniques and introduce a non-parametric approach to modeling distributions of complex datasets. |
Arantxa Casanova; Marlene Careil; Jakob Verbeek; Michal Drozdzal; Adriana Romero; | nips | 2021-11-20 |
| 179 | A Unified View of CGANs with and Without Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate that classifiers can be properly leveraged to improve cGANs. |
Si-An Chen; Chun-Liang Li; Hsuan-Tien Lin; | nips | 2021-11-20 |
| 180 | Learning to Generate Realistic Noisy Images Via Pixel-level Noise-aware Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this problem, this work investigates how to generate realistic noisy images. |
YUANHAO CAI et. al. | nips | 2021-11-20 |
| 181 | Projected GANs Converge Faster Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the finding that the discriminator cannot fully exploit features from deeper layers of the pretrained model, we propose a more effective strategy that mixes features across channels and resolutions. |
Axel Sauer; Kashyap Chitta; Jens M�ller; Andreas Geiger; | nips | 2021-11-20 |
| 182 | Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this gap via a comprehensive investigation on the impact of network width and depth on the robustness of adversarially trained DNNs. |
HANXUN HUANG et. al. | nips | 2021-11-20 |
| 183 | Shift Invariance Can Reduce Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Using this, we prove that shift invariance in neural networks produces adversarial examples for the simple case of two classes, each consisting of a single image with a black or white dot on a gray background. |
Vasu Singla; Songwei Ge; Basri Ronen; David Jacobs; | nips | 2021-11-20 |
| 184 | Do Wider Neural Networks Really Help Adversarial Robustness? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we carefully examine the relationship between network width and model robustness. |
Boxi Wu; Jinghui Chen; Deng Cai; Xiaofei He; Quanquan Gu; | nips | 2021-11-20 |
| 185 | Adversarial Examples Make Strong Poisons Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that adversarial examples, originally intended for attacking pre-trained models, are even more effective for data poisoning than recent methods designed specifically for poisoning. |
LIAM FOWL et. al. | nips | 2021-11-20 |
| 186 | Can We Have It All? On The Trade-off Between Spatial and Adversarial Robustness of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we prove a quantitative trade-off between spatial and adversarial robustness in a simple statistical setting. |
Sandesh Kamath; Amit Deshpande; Subrahmanyam Kambhampati Venkata; Vineeth N Balasubramanian; | nips | 2021-11-20 |
| 187 | Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a neural ODE with Lyapunov-stable equilibrium points for defending against adversarial attacks (SODEF). |
Qiyu Kang; Yang Song; Qinxu Ding; Wee Peng Tay; | nips | 2021-11-20 |
| 188 | Adversarial Graph Augmentation to Improve Graph Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a novel principle, termed adversarial-GCL (\textit{AD-GCL}), which enables GNNs to avoid capturing redundant information during the training by optimizing adversarial graph augmentation strategies used in GCL. |
Susheel Suresh; Pan Li; Cong Hao; Jennifer Neville; | nips | 2021-11-20 |
| 189 | Towards Efficient and Effective Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we bridge this performance gap by introducing a novel Nuclear-Norm regularizer on network predictions to enforce function smoothing in the vicinity of data samples. |
Gaurang Sriramanan; Sravanti Addepalli; Arya Baburaj; Venkatesh Babu R; | nips | 2021-11-20 |
| 190 | Neural Architecture Dilation for Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: From the neural architecture perspective, this paper aims to improve the adversarial robustness of the backbone CNNs that have a satisfactory accuracy. |
Yanxi Li; Zhaohui Yang; Yunhe Wang; Chang Xu; | nips | 2021-11-20 |
| 191 | Not All Low-Pass Filters Are Robust in Graph Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the theory, we present GCN-LFR, a general robust co-training paradigm for GCN-based models, that encourages transferring the robustness of low-frequency components with an auxiliary neural network. |
HENG CHANG et. al. | nips | 2021-11-20 |
| 192 | A Little Robustness Goes A Long Way: Leveraging Robust Features for Targeted Transfer Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we show that training the source classifier to be slightly robust-that is, robust to small-magnitude adversarial examples—substantially improves the transferability of class-targeted and representation-targeted adversarial attacks, even between architectures as different as convolutional neural networks and transformers. |
Jacob Springer; Melanie Mitchell; Garrett Kenyon; | nips | 2021-11-20 |
| 193 | Adversarial Examples in Multi-Layer Random ReLU Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the phenomenon of adversarial examples in ReLU networks with independent Gaussian parameters. |
Peter Bartlett; Sebastien Bubeck; Yeshwanth Cherapanamjeri; | nips | 2021-11-20 |
| 194 | Neural Population Geometry Reveals The Role of Stochasticity in Robust Perception Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, using recently developed geometrical techniques from computational neuroscience, we investigate how adversarial perturbations influence the internal representations of standard, adversarially trained, and biologically-inspired stochastic networks. |
JOEL DAPELLO et. al. | nips | 2021-11-20 |
| 195 | Encoding Robustness to Image Style Via Adversarial Feature Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our proposed method, Adversarial Batch Normalization (AdvBN), is a single network layer that generates worst-case feature perturbations during training. By fine-tuning neural networks on adversarial feature distributions, we observe improved robustness of networks to various unseen distributional shifts, including style variations and image corruptions. |
Manli Shu; Zuxuan Wu; Micah Goldblum; Tom Goldstein; | nips | 2021-11-20 |
| 196 | Clustering Effect of Adversarial Robust Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we interpret adversarial robustness from the perspective of linear components, and find that there exist some statistical properties for comprehensively robust models. |
Yang Bai; Xin Yan; Yong Jiang; Shu-Tao Xia; Yisen Wang; | nips | 2021-11-20 |
| 197 | Adversarial Examples for K-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an algorithm for evaluating the adversarial robustness of $k$-nearest neighbor classification, i.e., finding a minimum-norm adversarial example. |
Chawin Sitawarin; Evgenios Kornaropoulos; Dawn Song; David Wagner; | nips | 2021-11-20 |
| 198 | Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found Within Randomly Initialized Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: \textbf{Interestingly, we discover for the first time that there exist subnetworks with inborn robustness, matching or surpassing the robust accuracy of the adversarially trained networks with comparable model sizes, within randomly initialized networks without any model training}, indicating that adversarial training on model weights is not indispensable towards adversarial robustness. |
YONGGAN FU et. al. | nips | 2021-11-20 |
| 199 | Improving Calibration Through The Relationship with Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the connection between adversarial robustness and calibration and find that the inputs for which the model is sensitive to small perturbations (are easily attacked) are more likely to have poorly calibrated predictions. |
Yao Qin; Xuezhi Wang; Alex Beutel; Ed Chi; | nips | 2021-11-20 |
| 200 | Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier. |
Zifeng Wang; Tong Jian; Aria Masoomi; Stratis Ioannidis; Jennifer Dy; | nips | 2021-11-20 |
| 201 | Adversarial Teacher-Student Representation Learning for Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To extract and leverage the information which exhibits sufficient generalization ability, we propose a simple yet effective approach of Adversarial Teacher-Student Representation Learning, with the goal of deriving the domain generalizable representations via generating and exploring out-of-source data distributions. |
Fu-En Yang; Yuan-Chia Cheng; Zu-Yun Shiau; Yu-Chiang Frank Wang; | nips | 2021-11-20 |
| 202 | Adversarial Feature Desensitization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel approach to adversarial robustness, which builds upon the insights from the domain adaptation field. |
POUYA BASHIVAN et. al. | nips | 2021-11-20 |
| 203 | Adversarial Attacks on Graph Classifiers Via Bayesian Optimisation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel Bayesian optimisation-based attack method for graph classification models. |
XINGCHEN WAN et. al. | nips | 2021-11-20 |
| 204 | Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this problem, we propose the method of Generalized Depthwise-Separable (GDWS) convolution – an efficient, universal, post-training approximation of a standard 2D convolution. |
Hassan Dbouk; Naresh Shanbhag; | nips | 2021-11-20 |
| 205 | Predify: Augmenting Deep Neural Networks with Brain-inspired Predictive Coding Dynamics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we explore whether this shortcoming may be partly addressed by incorporating brain-inspired recurrent dynamics in deep convolutional networks. |
BHAVIN CHOKSI et. al. | nips | 2021-11-20 |
| 206 | Contrastive Learning for Neural Topic Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address those issues, we revisit the adversarial topic architecture in the view point of mathematical analysis, propose a novel approach to re-formulate discriminative goal as an optimization problem, and design a novel sampling method which facilitates the integration of external variables. |
Thong Nguyen; Anh Tuan Luu; | nips | 2021-11-20 |
| 207 | Adversarial Intrinsic Motivation for Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate whether one such objective, the Wasserstein-1 distance between a policy’s state visitation distribution and a target distribution, can be utilized effectively for reinforcement learning (RL) tasks. |
Ishan Durugkar; Mauricio Tec; Scott Niekum; Peter Stone; | nips | 2021-11-20 |
| 208 | A Single Gradient Step Finds Adversarial Examples on Random Two-layers Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In fact we prove that a single step of gradient descent suffices. We also show this result for any subexponential width random neural network with smooth activation function. |
Sebastien Bubeck; Yeshwanth Cherapanamjeri; Gauthier Gidel; Remi Tachet des Combes; | nips | 2021-11-20 |
| 209 | Learning Transferable Adversarial Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we, therefore, investigate the transferability of generated perturbations when the conditions at inference time differ from the training ones in terms of the target architecture, target data, and target task. |
Krishna kanth Nakka; Mathieu Salzmann; | nips | 2021-11-20 |
| 210 | Improving Compositionality of Neural Networks By Decoding Representations to Inputs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: With this as motivation, we take a modest first step towards improving deep learning programs by jointly training a generative model to constrain neural network activations to decode back to inputs. |
Mike Wu; Noah Goodman; Stefano Ermon; | nips | 2021-11-20 |
| 211 | Towards Efficiently Evaluating The Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework called Attack-Inspired GAN (AI-GAN) to generate adversarial examples conditionally. |
TAO BAI et. al. | arxiv-cs.LG | 2021-11-19 |
| 212 | Adversarial Deep Learning for Online Resource Allocation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To ensure better convergence of the algorithm network (to the desired online algorithm), we propose a novel per-round update method to handle sequential decision making to break complex dependency among different rounds so that update can be done for every possible action, instead of only sampled actions. |
Bingqian Du; Zhiyi Huang; Chuan Wu; | arxiv-cs.LG | 2021-11-19 |
| 213 | Enhanced Countering Adversarial Attacks Via Input Denoising and Feature Restoring Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome the weakness of the existing defense methods against adversarial attacks, which damages the information on the original samples, leading to the decrease of the target classifier accuracy, this paper presents an enhanced countering adversarial attack method IDFR (via Input Denoising and Feature Restoring). |
YANNI LI et. al. | arxiv-cs.CV | 2021-11-19 |
| 214 | Meta Adversarial Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show the existence of a meta adversarial perturbation (MAP), a better initialization that causes natural images to be misclassified with high probability after being updated through only a one-step gradient ascent update, and propose an algorithm for computing such perturbations. |
Chia-Hung Yuan; Pin-Yu Chen; Chia-Mu Yu; | arxiv-cs.LG | 2021-11-19 |
| 215 | TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Through extensive experiments on the large-scale visual classification task, ImageNet with evaluations across its entire validation set of 50,000 images, we demonstrate the realistic threat from TnTs and the robustness of the attack. |
Bao Gia Doan; Minhui Xue; Shiqing Ma; Ehsan Abbasnejad; Damith C. Ranasinghe; | arxiv-cs.CV | 2021-11-18 |
| 216 | One-Shot Generative Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work aims at transferring a Generative Adversarial Network (GAN) pre-trained on one image domain to a new domain referring to as few as just one target image. |
CEYUAN YANG et. al. | arxiv-cs.CV | 2021-11-18 |
| 217 | A Review of Adversarial Attack and Defense for Classification Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper aims to introduce this topic and its latest developments to the statistical community, primarily focusing on the generation and guarding of adversarial examples. |
Yao Li; Minhao Cheng; Cho-Jui Hsieh; Thomas C. M. Lee; | arxiv-cs.CR | 2021-11-18 |
| 218 | Generating Unrestricted 3D Adversarial Point Clouds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an Adversarial Graph-Convolutional Generative Adversarial Network (AdvGCGAN) to generate visually realistic adversarial 3D point clouds from scratch. |
Xuelong Dai; Yanjie Li; Hua Dai; Bin Xiao; | arxiv-cs.CV | 2021-11-17 |
| 219 | SeCGAN: Parallel Conditional Generative Adversarial Networks for Face Editing Via Semantic Consistency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose SeCGAN, a novel label-guided cGAN for editing face images utilising semantic information without the need to specify target semantic masks. |
Jiaze Sun; Binod Bhattarai; Zhixiang Chen; Tae-Kyun Kim; | arxiv-cs.CV | 2021-11-17 |
| 220 | Do Not Trust Prediction Scores for Membership Inference Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Membership inference attacks (MIAs) aim to determine whether a specific sample was used to train a predictive model. |
Dominik Hintersdorf; Lukas Struppek; Kristian Kersting; | arxiv-cs.LG | 2021-11-17 |
| 221 | MASS: Mobile Autonomous Station Simulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a set of tools to replay wireless network traffic traces, while preserving the privacy of the original traces. |
Thomas Sandholm; Sayandev Mukherjee; | arxiv-cs.NI | 2021-11-17 |
| 222 | Self-Attending Task Generative Adversarial Network for Realistic Satellite Image Creation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a self-attending task generative adversarial network (SATGAN) and apply it to the problem of augmenting synthetic high contrast scientific imagery of resident space objects with realistic noise patterns and sensor characteristics learned from collected data. |
Nathan Toner; Justin Fletcher; | arxiv-cs.LG | 2021-11-17 |
| 223 | Attacking Deep Learning AI Hardware with Universal Adversarial Perturbation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we demonstrate an attack strategy that when activated by rogue means (e.g., malware, trojan) can bypass these existing countermeasures by augmenting the adversarial noise at the AI hardware accelerator stage. |
Mehdi Sadi; B. M. S. Bahar Talukder; Kaniz Mishty; Md Tauhidur Rahman; | arxiv-cs.CR | 2021-11-17 |
| 224 | Towards Generating Real-World Time Series Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel generative framework for RTS data – RTSGAN to tackle the aforementioned challenges. |
HENGZHI PEI et. al. | arxiv-cs.LG | 2021-11-16 |
| 225 | Synthesis-Guided Feature Learning for Cross-Spectral Periocular Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel approach to cross-spectral periocular verification that primarily focuses on learning a mapping from visible and NIR periocular images to a shared latent representational subspace, and supports this effort by simultaneously learning intra-spectral image reconstruction. |
Domenick Poster; Nasser Nasrabadi; | arxiv-cs.CV | 2021-11-16 |
| 226 | Detecting AutoAttack Perturbations in The Frequency Domain Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the spatial and frequency domain properties of AutoAttack and propose an alternative defense. |
Peter Lorenz; Paula Harder; Dominik Strassel; Margret Keuper; Janis Keuper; | arxiv-cs.CV | 2021-11-16 |
| 227 | Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, we investigate the robustness of BNNs to white-box attacks using multiple Bayesian neural architectures. |
Adaku Uchendu; Daniel Campoy; Christopher Menart; Alexandra Hildenbrandt; | arxiv-cs.LG | 2021-11-16 |
| 228 | Improving The Robustness and Accuracy of Biomedical Language Models Through Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We implemented various adversarial attack methods to test the NLP systems in different attack scenarios. |
Milad Moradi; Matthias Samwald; | arxiv-cs.CL | 2021-11-16 |
| 229 | Property Inference Attacks Against GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a general attack pipeline that can be tailored to two attack scenarios, including the full black-box setting and partial black-box setting. |
Junhao Zhou; Yufei Chen; Chao Shen; Yang Zhang; | arxiv-cs.CR | 2021-11-15 |
| 230 | TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel architecture for synthetically generating time-series data with the use of Variational Auto-Encoders (VAEs). |
Abhyuday Desai; Cynthia Freeman; Zuhui Wang; Ian Beaver; | arxiv-cs.LG | 2021-11-15 |
| 231 | Lifelong Vehicle Trajectory Prediction Framework Based on Generative Replay Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To maintain consistent performance as a vehicle driving around different cities, it is crucial to adapt to changing traffic circumstances and achieve lifelong trajectory prediction model. |
Peng Bao; Zonghai Chen; Jikai Wang; Deyun Dai; Hao Zhao; | arxiv-cs.RO | 2021-11-14 |
| 232 | Generating Band-Limited Adversarial Surfaces Using Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this technical report we suggest a neural network that generates the attacks. |
Roee Ben Shlomo; Yevgeniy Men; Ido Imanuel; | arxiv-cs.CV | 2021-11-14 |
| 233 | Introducing Variational Autoencoders to High School Students Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes the lesson design and shares insights from the pilot studies with 22 students. |
Zhuoyue Lyu; Safinah Ali; Cynthia Breazeal; | arxiv-cs.CY | 2021-11-12 |
| 234 | Resilient Consensus-based Multi-agent Reinforcement Learning with Function Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider a fully decentralized network, where each agent receives a local reward and observes the global state and action. |
Martin Figura; Yixuan Lin; Ji Liu; Vijay Gupta; | arxiv-cs.LG | 2021-11-12 |
| 235 | Training Generative Adversarial Networks with Adaptive Composite Gradient Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposed the adaptive Composite Gradients (ACG) method, linearly convergent in bilinear games under suitable settings. |
Huiqing Qi; Fang Li; Shengli Tan; Xiangyun Zhang; | arxiv-cs.LG | 2021-11-09 |
| 236 | Sparse Adversarial Video Attacks with Spatial Transformations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an adversarial attack strategy on videos, called DeepSAVA. |
Ronghui Mu; Wenjie Ruan; Leandro Soriano Marcolino; Qiang Ni; | arxiv-cs.CV | 2021-11-09 |
| 237 | Tightening The Approximation Error of Adversarial Risk with Auto Loss Function Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we establish the tightening of the approximation error as an optimization problem and try to solve it with an algorithm. |
Pengfei Xia; Ziqiang Li; Bin Li; | arxiv-cs.LG | 2021-11-09 |
| 238 | Accelerating GAN Training Using Highly Parallel Hardware on Public Cloud Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: More specifically, we parallelize the training process on multiple GPUs and Google Tensor Processing Units (TPU) and we compare two algorithms: the TensorFlow built-in logic and a custom loop, optimised to have higher control of the elements assigned to each GPU worker or TPU core. |
RENATO CARDOSO et. al. | arxiv-cs.LG | 2021-11-08 |
| 239 | SL-CycleGAN: Blind Motion Deblurring in Cycles Using Sparse Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce an end-to-end generative adversarial network (GAN) based on sparse learning for single image blind motion deblurring, which we called SL-CycleGAN. |
Ali Syed Saqlain; Li-Yun Wang; Fang Fang; | arxiv-cs.CV | 2021-11-07 |
| 240 | Teamwork Makes Von Neumann Work: Min-Max Optimization in Two-Team Zero-Sum Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we present a family of team games whose induced utility is \emph{non} multi-linear with \emph{non} attractive \emph{per-se} mixed Nash Equilibria, as strict saddle points of the underlying optimization landscape. |
Fivos Kalogiannis; Ioannis Panageas; Emmanouil-Vasileios Vlatakis-Gkaragkounis; | arxiv-cs.GT | 2021-11-07 |
| 241 | Generative Dynamic Patch Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that GDPA is a generic attack framework that can produce dynamic/static and visible/invisible patches with a few configuration changes. |
Xiang Li; Shihao Ji; | arxiv-cs.CV | 2021-11-07 |
| 242 | KnowMAN: Weakly Supervised Multinomial Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose KnowMAN, an adversarial scheme that enables to control influence of signals associated with specific labeling functions. |
Luisa M?rz; Ehsaneddin Asgari; Fabienne Braune; Franziska Zimmermann; Benjamin Roth; | emnlp | 2021-11-05 |
| 243 | A Deep Learning Generative Model Approach for Image Synthesis of Plant Leaves Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We aim to dispose of a source of training samples for AI applications for modern crop management. |
Alessandrop Benfenati; Davide Bolzi; Paola Causin; Roberto Oberti; | arxiv-cs.CV | 2021-11-05 |
| 244 | ActFloor-GAN: Activity-Guided Adversarial Networks for Human-Centric Floorplan Design Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel two-stage approach for automated floorplan design in residential buildings with a given exterior wall boundary. |
SHIDONG WANG et. al. | arxiv-cs.GR | 2021-11-05 |
| 245 | Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose the Adversarial Mixing Policy (AMP), organized in a min-max-rand formulation, to relax the Locally Linear Constraints in Mixup. |
Guang Liu; Yuzhao Mao; Huang Hailong; Gao Weiguo; Li Xuan; | emnlp | 2021-11-05 |
| 246 | Generative Context Pair Selection for Multi-hop Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a generative context selection model for multi-hop QA that reasons about how the given question could have been generated given a context pair and not just independent contexts. |
DHEERU DUA et. al. | emnlp | 2021-11-05 |
| 247 | On The Transferability of Adversarial Attacks Against Neural Text Classifier Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on these studies, we propose a genetic algorithm to find an ensemble of models that can be used to induce adversarial examples to fool almost all existing models. |
Liping Yuan; Xiaoqing Zheng; Yi Zhou; Cho-Jui Hsieh; Kai-Wei Chang; | emnlp | 2021-11-05 |
| 248 | Searching for An Effective Defender: Benchmarking Defense Against Adversarial Word Substitution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we seek to fill the gap of systematic studies through comprehensive researches on understanding the behavior of neural text classifiers trained by various defense methods under representative adversarial attacks. |
ZONGYI LI et. al. | emnlp | 2021-11-05 |
| 249 | Physics-Guided Generative Adversarial Networks for Sea Subsurface Temperature Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework based on generative adversarial network (GAN) combined with numerical model to predict sea subsurface temperature. |
YUXIN MENG et. al. | arxiv-cs.LG | 2021-11-04 |
| 250 | Generating Diverse Realistic Laughter for Interactive Art Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an interactive art project to make those rendered invisible by the COVID-19 crisis and its concomitant solitude reappear through the welcome melody of laughter, and connections created and explored through advanced laughter synthesis approaches. |
M. MEHDI AFSAR et. al. | arxiv-cs.LG | 2021-11-04 |
| 251 | GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Under such a class of discriminator (or critic) functions, we present Gradient Normalization (GraN), a novel input-dependent normalization method, which guarantees a piecewise K-Lipschitz constraint in the input space. |
Vineeth S. Bhaskara; Tristan Aumentado-Armstrong; Allan Jepson; Alex Levinshtein; | arxiv-cs.LG | 2021-11-04 |
| 252 | Generative Adversarial Network for Probabilistic Forecast of Random Dynamical System Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a deep learning model for data-driven simulations of random dynamical systems without a distributional assumption. |
Kyongmin Yeo; Zan Li; Wesley M. Gifford; | arxiv-cs.LG | 2021-11-04 |
| 253 | Discriminator Synthesis: On Reusing The Other Half of Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to use the latter and show a way to use the features it has learned from the training dataset to both alter an image and generate one from scratch. |
Diego Porres; | arxiv-cs.CV | 2021-11-03 |
| 254 | Improving Model Compatibility of Generative Adversarial Networks By Boundary Calibration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To improve GAN in terms of model compatibility, we propose Boundary-Calibration GANs (BCGANs), which leverage the boundary information from a set of pre-trained classifiers using the original data. |
Si-An Chen; Chun-Liang Li; Hsuan-Tien Lin; | arxiv-cs.LG | 2021-11-03 |
| 255 | LTD: Low Temperature Distillation for Robust Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we proposed a method, called Low Temperature Distillation (LTD), which is based on the knowledge distillation framework to generate the desired soft labels. |
Erh-Chung Chen; Che-Rung Lee; | arxiv-cs.CV | 2021-11-03 |
| 256 | Convolutional Generative Adversarial Imputation Networks for Spatio-temporal Missing Data in Storm Surge Simulations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, the Generative Adversarial Imputation Nets (GAIN) performance is improved by applying convolutional neural networks instead of fully connected layers to better capture the correlation of data and promote learning from the adjacent surge points. |
Ehsan Adeli; Jize Zhang; Alexandros A. Taflanidis; | arxiv-cs.LG | 2021-11-02 |
| 257 | Spiking Generative Adversarial Networks With A Neural Network Discriminator: Local Training, Bayesian Models, and Continual Meta-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, in order to fully leverage the time-encoding capacity of spikes, this work proposes to train SNNs so as to match distributions of spiking signals rather than individual spiking signals. |
Bleema Rosenfeld; Osvaldo Simeone; Bipin Rajendran; | arxiv-cs.LG | 2021-11-02 |
| 258 | Bounds All Around: Training Energy-based Models with Bidirectional Bounds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a bidirectional bound on the EBM log-likelihood, such that we maximize a lower bound and minimize an upper bound when solving the minimax game. |
Cong Geng; Jia Wang; Zhiyong Gao; Jes Frellsen; Søren Hauberg; | arxiv-cs.LG | 2021-11-01 |
| 259 | FREGAN : An Application of Generative Adversarial Networks in Enhancing The Frame Rate of Videos Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigated the GAN model and proposed FREGAN for the enhancement of frame rate in videos. |
Rishik Mishra; Neeraj Gupta; Nitya Shukla; | arxiv-cs.CV | 2021-11-01 |
| 260 | RefineGAN: Universally Generating Waveform Better Than Ground Truth with Highly Accurate Pitch and Intensity Responses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose RefineGAN, a high-fidelity neural vocoder with faster-than-real-time generation capability, and focused on the robustness, pitch and intensity accuracy, and full-band audio generation. |
Shengyuan Xu; Wenxiao Zhao; Jing Guo; | arxiv-cs.SD | 2021-11-01 |
| 261 | MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, we propose a framework that a priori models physical attributes of the face such as 3D shape, albedo, pose, and lighting explicitly, thus providing disentanglement by design. |
SAFA C. MEDIN et. al. | arxiv-cs.CV | 2021-11-01 |
| 262 | Attention-Guided Generative Adversarial Network for Whisper to Normal Speech Conversion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a novel attention-guided generative adversarial network model incorporating an autoencoder, a Siamese neural network, and an identity mapping loss function for whisper to normal speech conversion (AGAN-W2SC) is proposed. |
Teng Gao; Jian Zhou; Huabin Wang; Liang Tao; Hon Keung Kwan; | arxiv-cs.SD | 2021-11-01 |
| 263 | Projected GANs Converge Faster IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the finding that the discriminator cannot fully exploit features from deeper layers of the pretrained model, we propose a more effective strategy that mixes features across channels and resolutions. |
Axel Sauer; Kashyap Chitta; Jens Müller; Andreas Geiger; | arxiv-cs.CV | 2021-11-01 |
| 264 | Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose DP-Sinkhorn, a novel optimal transport-based generative method for learning data distributions from private data with differential privacy. |
Tianshi Cao; Alex Bie; Arash Vahdat; Sanja Fidler; Karsten Kreis; | arxiv-cs.LG | 2021-11-01 |
| 265 | ECG Synthesis with Neural ODE and GAN Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we used Neural ODE based model to generate synthetic sine waves and synthetic ECG. |
Mansura Habiba; Eoin Borphy; Barak A. Pearlmutter; Tomas Ward; | arxiv-cs.LG | 2021-10-30 |
| 266 | Visual Explanations for Convolutional Neural Networks Via Latent Traversal of Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Using COVID-19 chest X-rays, we present a method for interpreting what a CNN has learned by utilizing Generative Adversarial Networks (GANs). |
Amil Dravid; Aggelos K. Katsaggelos; | arxiv-cs.CV | 2021-10-29 |
| 267 | Improving The Quality of Generative Models Through Smirnov Transformation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel activation function to be used as output of the generator agent. |
Ángel González-Prieto; Alberto Mozo; Sandra Gómez-Canaval; Edgar Talavera; | arxiv-cs.LG | 2021-10-29 |
| 268 | Ε-weakened Robustness of Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a notation of $\varepsilon$-weakened robustness for analyzing the reliability and stability of deep neural networks (DNNs). |
PEI HUANG et. al. | arxiv-cs.LG | 2021-10-29 |
| 269 | AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this observation, we propose the adversarial extreme value analysis(AEVA) to detect backdoors in black-box neural networks. |
Junfeng Guo; Ang Li; Cong Liu; | arxiv-cs.LG | 2021-10-28 |
| 270 | Bridge The Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge this gap, we propose a general framework to adapt existing gradient-based methods to craft textual adversarial samples. |
Lifan Yuan; Yichi Zhang; Yangyi Chen; Wei Wei; | arxiv-cs.CL | 2021-10-28 |
| 271 | NIDA-CLIFGAN: Natural Infrastructure Damage Assessment Through Efficient Classification Combining Contrastive Learning, Information Fusion and Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Accordingly, the paper demonstrates a systematic effort to achieve efficient building damage classification. |
JIE WEI et. al. | arxiv-cs.LG | 2021-10-27 |
| 272 | Fuzzy Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces techniques that show improvement in the GANs’ regression capability through mean absolute error (MAE) and mean squared error (MSE). |
Ryan Nguyen; Shubhendu Kumar Singh; Rahul Rai; | arxiv-cs.LG | 2021-10-27 |
| 273 | Validation Methods for Energy Time Series Scenarios from Deep Generative Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We apply the four validation methods to both the historical and the generated data and discuss the interpretation of validation results as well as common mistakes, pitfalls, and limitations of the validation methods. |
EIKE CRAMER et. al. | arxiv-cs.LG | 2021-10-27 |
| 274 | CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate GNNs from the lens of weight and feature loss landscapes, i.e., the loss changes with respect to model weights and node features, respectively. To tackle this problem, we construct the co-adversarial perturbation (CAP) optimization problem in terms of weights and features, and design the alternating adversarial perturbation algorithm to flatten the weight and feature loss landscapes alternately. |
HAOTIAN XUE et. al. | arxiv-cs.LG | 2021-10-27 |
| 275 | Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this problem, we propose the method of Generalized Depthwise-Separable (GDWS) convolution — an efficient, universal, post-training approximation of a standard 2D convolution. |
Hassan Dbouk; Naresh R. Shanbhag; | arxiv-cs.LG | 2021-10-27 |
| 276 | Training Wasserstein GANs Without Gradient Penalties Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a stable method to train Wasserstein generative adversarial networks. |
Dohyun Kwon; Yeoneung Kim; Guido Montúfar; Insoon Yang; | arxiv-cs.LG | 2021-10-26 |
| 277 | Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a comprehensive review of the main approaches for adversarial attacks and defenses in the context of social media applications with a particular focus on key challenges and future research directions. |
IZZAT ALSMADI et. al. | arxiv-cs.CL | 2021-10-26 |
| 278 | Frequency Centric Defense Mechanisms Against Adversarial Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Adversarial example (AE) aims at fooling a Convolution Neural Network by introducing small perturbations in the input image.The proposed work uses the magnitude and phase of the Fourier Spectrum and the entropy of the image to defend against AE. |
Sanket B. Shah; Param Raval; Harin Khakhi; Mehul S. Raval; | arxiv-cs.CV | 2021-10-26 |
| 279 | Can’t Fool Me: Adversarially Robust Transformer for Video Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to bridge this gap. |
Divya Choudhary; Palash Goyal; Saurabh Sahu; | arxiv-cs.CV | 2021-10-26 |
| 280 | Defensive Tensorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose defensive tensorization, an adversarial defence technique that leverages a latent high-order factorization of the network. |
ADRIAN BULAT et. al. | arxiv-cs.LG | 2021-10-26 |
| 281 | The Nuts and Bolts of Adopting Transformer in GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we conduct a comprehensive empirical study to investigate the properties of Transformer in GAN for high-fidelity image synthesis. |
Rui Xu; Xiangyu Xu; Kai Chen; Bolei Zhou; Chen Change Loy; | arxiv-cs.CV | 2021-10-25 |
| 282 | Negotiating Networks in Oligopoly Markets for Price-Sensitive Products Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel framework to learn functions that estimate decisions of sellers and buyers simultaneously in an oligopoly market for a price-sensitive product. |
Naman Shukla; Kartik Yellepeddi; | arxiv-cs.LG | 2021-10-25 |
| 283 | EarthGAN: Can We Visualize The Earth’s Mantle Convection Using A Surrogate Model? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this research, we seek to build a surrogate model, using a generative adversarial network, to allow for the visualization of the Earth’s Mantle Convection data set on readily accessible hardware. |
Tim von Hahn; Chris K. Mechefske; | arxiv-cs.LG | 2021-10-25 |
| 284 | Towards Realistic Market Simulations: A Generative Adversarial Networks Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, multi-agent simulation presents a natural bottom-up approach to emulating agent interaction in financial markets. |
ANDREA COLETTA et. al. | arxiv-cs.AI | 2021-10-25 |
| 285 | Generating Watermarked Adversarial Texts Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to tackle with this problem, we present a general framework for generating watermarked adversarial text examples. |
Mingjie Li; Hanzhou Wu; Xinpeng Zhang; | arxiv-cs.CR | 2021-10-25 |
| 286 | Quality Map Fusion for Adversarial Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we improve image quality adversarially by introducing a novel quality map fusion technique that harnesses image features similar to the HVS and the perceptual properties of a deep convolutional neural network (DCNN). |
Uche Osahor; Nasser M. Nasrabadi; | arxiv-cs.CV | 2021-10-23 |
| 287 | Face Sketch to Photo Translation Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a method for converting an input facial sketch to a colorful photo without the need for any paired dataset. |
Nastaran Moradzadeh Farid; Maryam Saeedi Fard; Ahmad Nickabadi; | arxiv-cs.CV | 2021-10-23 |
| 288 | A Layer-wise Adversarial-aware Quantization Optimization for Improving Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we find that adversarially-trained neural networks are more vulnerable to quantization loss than plain models. |
Chang Song; Riya Ranjan; Hai Li; | arxiv-cs.LG | 2021-10-23 |
| 289 | ADC: Adversarial Attacks Against Object Detection That Evade Context Consistency Checks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we propose an adaptive framework to generate examples that subvert such defenses, namely, Adversarial attacks against object Detection that evade Context consistency checks (ADC). |
MINGJUN YIN et. al. | arxiv-cs.CV | 2021-10-23 |
| 290 | Generative Adversarial Networks for Non-Raytraced Global Illumination on Older GPU Hardware Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We give an overview of the different rendering methods and we demonstrate that the use of a Generative Adversarial Networks (GAN) for Global Illumination (GI) gives a superior quality rendered image to that of a rasterisations image. |
Jared Harris-Dewey; Richard Klein; | arxiv-cs.CV | 2021-10-22 |
| 291 | Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a systematic literature review of the applications of GANs in anomaly detection, covering 128 papers on the subject. |
Mikael Sabuhi; Ming Zhou; Cor-Paul Bezemer; Petr Musilek; | arxiv-cs.LG | 2021-10-22 |
| 292 | How and When Adversarial Robustness Transfers in Knowledge Distillation? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that standard KD training fails to preserve adversarial robustness, and we propose KD with input gradient alignment (KDIGA) for remedy. |
Rulin Shao; Jinfeng Yi; Pin-Yu Chen; Cho-Jui Hsieh; | arxiv-cs.LG | 2021-10-22 |
| 293 | Adversarial Robustness for Latent Models: Revisiting The Robust-standard Accuracies Tradeoff Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we revisit this tradeoff for latent models and argue that this tradeoff is mitigated when the data enjoys a low-dimensional structure. |
Adel Javanmard; Mohammad Mehrabi; | arxiv-cs.LG | 2021-10-22 |
| 294 | Generative Adversarial Graph Convolutional Networks for Human Action Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Kinetic-GAN, a novel architecture that leverages the benefits of Generative Adversarial Networks and Graph Convolutional Networks to synthesise the kinetics of the human body. |
BRUNO DEGARDIN et. al. | arxiv-cs.CV | 2021-10-21 |
| 295 | An Empirical Study on GANs with Margin Cosine Loss and Relativistic Discriminator Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we perform an empirical study on the impact of several loss functions on the performance of standard GAN models, Deep Convolutional Generative Adversarial Networks (DCGANs). |
Cuong V. Nguyen; Tien-Dung Cao; Tram Truong-Huu; Khanh N. Pham; Binh T. Nguyen; | arxiv-cs.CV | 2021-10-21 |
| 296 | PROVES: Establishing Image Provenance Using Semantic Signatures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel architecture for preserving the provenance of semantic information in images to make them less susceptible to deep fake attacks. |
MINGYANG XIE et. al. | arxiv-cs.CV | 2021-10-21 |
| 297 | On Some Theoretical Limitations of Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a new result based on Extreme Value Theory showing that GANs can’t generate heavy tailed distributions. |
Benoît Oriol; Alexandre Miot; | arxiv-cs.LG | 2021-10-21 |
| 298 | Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To cope with this problem, by focusing on enhancing the difference between attributes, this paper proposes a novel model called Contrastive Attention Generative Adversarial Network (CA-GAN), which is inspired from contrastive training. |
LIUQING ZHAO et. al. | arxiv-cs.CV | 2021-10-21 |
| 299 | Super-resolution of Multiphase Materials By Combining Complementary 2D and 3D Image Data Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a method for combining information from pairs of distinct but complementary imaging techniques in order to accurately reconstruct the desired multi-phase, high resolution, representative, 3D images. |
Amir Dahari; Steve Kench; Isaac Squires; Samuel J. Cooper; | arxiv-cs.CV | 2021-10-21 |
| 300 | CAPTIVE: Constrained Adversarial Perturbations to Thwart IC Reverse Engineering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an approach to introduce cognitive perturbations, with the aid of adversarial machine learning, to the IC layout that could prevent the RE process from succeeding. We first construct a layer-by-layer image dataset of 45nm predictive technology. |
AMIR HOSEIN AFANDIZADEH ZARGARI et. al. | arxiv-cs.CR | 2021-10-21 |
| 301 | Deep Generative Models in Engineering Design: A Review Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a review and analysis of Deep Generative Learning models in engineering design. |
Lyle Regenwetter; Amin Heyrani Nobari; Faez Ahmed; | arxiv-cs.LG | 2021-10-20 |
| 302 | Adversarial Socialbot Learning Via Multi-Agent Deep Hierarchical Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This begs a question can adversaries, controlling socialbots, exploit AI techniques to their advantage? |
Thai Le; Long Tran-Thanh; Dongwon Lee; | arxiv-cs.SI | 2021-10-20 |
| 303 | Fine-Grained Control of Artistic Styles in Image Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to achieve this by embedding original artwork examples into a continuous style space. |
XIN MIAO et. al. | arxiv-cs.CV | 2021-10-19 |
| 304 | Three Attacks on Proof-of-Stake Ethereum Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Combining techniques from both refined attacks, we obtain a third attack which allows an adversary with vanishingly small fraction of stake and no control over network message propagation (assuming instead probabilistic message propagation) to cause even long-range consensus chain reorganizations. |
CASPAR SCHWARZ-SCHILLING et. al. | arxiv-cs.CR | 2021-10-19 |
| 305 | A Regularization Method to Improve Adversarial Robustness of Neural Networks for ECG Signal Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we proposed a regularization method to improve DNN robustness from the perspective of noise-to-signal ratio (NSR) for the application of ECG signal classification. |
Linhai Ma; Liang Liang; | arxiv-cs.LG | 2021-10-19 |
| 306 | Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a first attempt at adopting neural synthesis for this task. |
Marco Comunità; Huy Phan; Joshua D. Reiss; | arxiv-cs.SD | 2021-10-18 |
| 307 | Protecting Anonymous Speech: A Generative Adversarial Network Methodology for Removing Stylistic Indicators in Text Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a new approach to authorship anonymization by constructing a generative adversarial network that protects identity and optimizes for three different losses corresponding to anonymity, fluency, and content preservation. |
Rishi Balakrishnan; Stephen Sloan; Anil Aswani; | arxiv-cs.LG | 2021-10-18 |
| 308 | Continuation of Famous Art with AI: A Conditional Adversarial Network Inpainting Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work explores the application of image inpainting to continue famous artworks and produce generative art with a Conditional GAN. |
Jordan J. Bird; | arxiv-cs.CV | 2021-10-18 |
| 309 | Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording Devices Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, in this paper, we investigate several adversarial models for domain adaptation (DA) and their effect on the acoustic scene classification task. |
Stanisław Kacprzak; Konrad Kowalczyk; | arxiv-cs.SD | 2021-10-18 |
| 310 | Don’t Judge Me By My Face : An Indirect Adversarial Approach to Remove Sensitive Information From Multimodal Neural Representation in Asynchronous Job Video Interviews Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this article, we propose a new adversarial approach to remove sensitive information from the latent representation of neural networks without the need to collect any sensitive variable. |
Léo Hemamou; Arthur Guillon; Jean-Claude Martin; Chloé Clavel; | arxiv-cs.CV | 2021-10-18 |
| 311 | Towards Better Long-range Time Series Forecasting Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we utilize a Conditional Wasserstein GAN (CWGAN) and augment it with an error penalty term, leading to a new generative model which aims to generate high-quality synthetic time series data, called CWGAN-TS. |
Shiyu Liu; Mehul Motani; | arxiv-cs.LG | 2021-10-17 |
| 312 | Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose two variations of GAIL for autonomous navigation of a vehicle in the realistic CARLA simulation environment for urban scenarios. |
Gustavo Claudio Karl Couto; Eric Aislan Antonelo; | arxiv-cs.RO | 2021-10-16 |
| 313 | Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an adversarial attack framework by treating the prediction model as a black-box, i.e., assuming no knowledge of the model architecture, training data, and (hyper)parameters. |
Bibek Poudel; Weizi Li; | arxiv-cs.LG | 2021-10-16 |
| 314 | MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In response, we develop MaGNET, a novel and theoretically motivated latent space sampler for any pre-trained DGN, that produces samples uniformly distributed on the learned manifold. |
Ahmed Imtiaz Humayun; Randall Balestriero; Richard Baraniuk; | arxiv-cs.LG | 2021-10-15 |
| 315 | Pose-guided Generative Adversarial Net for Novel View Action Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we propose a novel framework named Pose-guided Action Separable Generative Adversarial Net (PAS-GAN), which utilizes pose to alleviate the difficulty of this task. |
Xianhang Li; Junhao Zhang; Kunchang Li; Shruti Vyas; Yogesh S Rawat; | arxiv-cs.CV | 2021-10-15 |
| 316 | Adversarial Attacks on ML Defense Models Competition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The participants were encouraged to develop stronger white-box attack algorithms to find the worst-case robustness of different defenses. |
YINPENG DONG et. al. | arxiv-cs.CV | 2021-10-15 |
| 317 | SpecSinGAN: Sound Effect Variation Synthesis Using Single-Image GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we introduce SpecSinGAN, an unconditional generative architecture that takes a single one-shot sound effect (e.g., a footstep; a character jump) and produces novel variations of it, as if they were different takes from the same recording session. |
Adrián Barahona-Ríos; Tom Collins; | arxiv-cs.SD | 2021-10-14 |
| 318 | RGB-D Image Inpainting Using Generative Adversarial Network with A Late Fusion Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by other tasks that use RGB and depth images (e.g., semantic segmentation and object detection), we propose late fusion approach that exploits the advantage of RGB and depth information each other. |
Ryo Fujii; Ryo Hachiuma; Hideo Saito; | arxiv-cs.CV | 2021-10-14 |
| 319 | Adversarial Examples By Perturbing High-level Features in Intermediate Decoder Layers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel method for creating adversarial examples. |
Vojtěch Čermák; Lukáš Adam; | arxiv-cs.CV | 2021-10-14 |
| 320 | Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore a data-driven approach that uses a generative adversarial network to create the song transition by learning from real-world DJ mixes. |
BO-YU CHEN et. al. | arxiv-cs.SD | 2021-10-13 |
| 321 | Improving Users’ Mental Model with Attention-directed Counterfactual Edits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that showing controlled counterfactual image-question examples are more effective at improving the mental model of users as compared to simply showing random examples. |
KAMRAN ALIPOUR et. al. | arxiv-cs.CV | 2021-10-13 |
| 322 | End-to-end Translation of Human Neural Activity to Speech with A Dual-dual Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an end-to-end model to translate human neural activity to speech directly, create a new electroencephalogram (EEG) datasets for participants with good attention by design a device to detect participants’ attention, and introduce a dual-dual generative adversarial network (Dual-DualGAN) (see Fig. 1 (c) and (d)) to address an end-to-end translation of human neural activity to speech (ET-CAS) problem by group labelling EEG signals and speech signals, inserting a transition domain to realize cross-domain mapping. |
Yina Guo; Xiaofei Zhang; Zhenying Gong; Anhong Wang; Wenwu Wang; | arxiv-cs.SD | 2021-10-13 |
| 323 | Identification of Attack-Specific Signatures in Adversarial Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that different attack algorithms produce adversarial examples which are distinct not only in their effectiveness but also in how they qualitatively affect their victims. |
Hossein Souri; Pirazh Khorramshahi; Chun Pong Lau; Micah Goldblum; Rama Chellappa; | arxiv-cs.LG | 2021-10-13 |
| 324 | Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper: we explore generative adversarial network (GAN) paradigms to learn unsupervised feature representations from wearable sensor data; and design a new GAN framework-Geometrically-Guided GAN or Guided-GAN-for the task. |
Alireza Abedin; Hamid Rezatofighi; Damith C. Ranasinghe; | arxiv-cs.LG | 2021-10-12 |
| 325 | Real Image Inversion Via Segments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this short report, we present a simple, yet effective approach to editing real images via generative adversarial networks (GAN). |
David Futschik; Michal Lukáč; Eli Shechtman; Daniel Sýkora; | arxiv-cs.CV | 2021-10-12 |
| 326 | Information Theoretic Structured Generative Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this special connection, a novel generative model framework called the structured generative model (SGM) is proposed that makes straightforward optimization possible, because costs are scale-invariant, avoiding high gradient variance while imposing less restrictions on absolute continuity, which is a huge advantage in parametric information theoretic optimization. |
Bo Hu; Shujian Yu; Jose C. Principe; | arxiv-cs.LG | 2021-10-12 |
| 327 | M2GAN: A Multi-Stage Self-Attention Network for Image Rain Removal on Autonomous Vehicles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new multi-stage multi-task recurrent generative adversarial network (M2GAN) to deal with challenging problems of raindrops hitting the car’s windshield. To demonstrate M2GAN, we introduce the first real-world dataset for rain removal on autonomous vehicles. |
Duc Manh Nguyen; Sang-Woong Lee; | arxiv-cs.CV | 2021-10-12 |
| 328 | Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we devote to study the security issues of GNN based VFL (GVFL), i.e., robustness against adversarial attacks. |
Jinyin Chen; Guohan Huang; Shanqing Yu; Wenrong Jiang; Chen Cui; | arxiv-cs.LG | 2021-10-12 |
| 329 | DecGAN: Decoupling Generative Adversarial Network Detecting Abnormal Neural Circuits for Alzheimer’s Disease Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, a novel decoupling generative adversarial network (DecGAN) is proposed to detect abnormal neural circuits for AD. |
JUNREN PAN et. al. | arxiv-cs.LG | 2021-10-11 |
| 330 | UnfairGAN: An Enhanced Generative Adversarial Network for Raindrop Removal from A Single Image Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an enhanced generative adversarial network to deal with the challenging problems of raindrops. To demonstrate UnfairGAN, we introduce a large dataset for training deep learning models of rain removal. |
Duc Manh Nguyen; Sang-Woong Lee; | arxiv-cs.CV | 2021-10-11 |
| 331 | Boosting Fast Adversarial Training with Learnable Adversarial Initialization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we boost fast AT with a sample-dependent adversarial initialization, i.e., an output from a generative network conditioned on a benign image and its gradient information from the target network. |
Xiaojun Jia; Yong Zhang; Baoyuan Wu; Jue Wang; Xiaochun Cao; | arxiv-cs.CV | 2021-10-11 |
| 332 | Parameterizing Activation Functions for Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study how using learnable PAFs can improve robustness in conjunction with adversarial training. |
Sihui Dai; Saeed Mahloujifar; Prateek Mittal; | arxiv-cs.LG | 2021-10-11 |
| 333 | Hiding Images Into Images with Real-world Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this problem, we introduce a generative deep network based method for hiding images into images while assuring high-quality extraction from the destructive synthesized images. We also pinpoint the weaknesses of the adversarial training for robustness in previous works and build our improved real-world attack simulator. |
QICHAO YING et. al. | arxiv-cs.CV | 2021-10-11 |
| 334 | Adversarial Attacks in A Multi-view Setting: An Empirical Study of The Adversarial Patches Inter-view Transferability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the effect of view angle on the effectiveness of an adversarial patch. |
Bilel Tarchoun; Ihsen Alouani; Anouar Ben Khalifa; Mohamed Ali Mahjoub; | arxiv-cs.CR | 2021-10-10 |
| 335 | Demystifying The Transferability of Adversarial Attacks in Computer Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to demystify the transferability threats in computer networks by studying the possibility of transferring adversarial examples. |
Ehsan Nowroozi; Mauro Conti; Yassine Mekdad; Mohammad Hajian Berenjestanaki; Abdeslam EL Fergougui; | arxiv-cs.CR | 2021-10-09 |
| 336 | Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, we seek a proactive and sustainable solution on deepfake detection, that is agnostic to the evolution of generative models, by introducing artificial fingerprints into the models. |
Ning Yu; Vladislav Skripniuk; Sahar Abdelnabi; Mario Fritz; | iccv | 2021-10-08 |
| 337 | Can Shape Structure Features Improve Model Robustness Under Diverse Adversarial Settings? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the findings that human visual system pays more attention to global structure (e.g., shapes) for recognition while CNNs are biased towards local texture features in images, in this work we aim to analyze whether "edge features" could improve the recognition robustness in these scenarios, and if so, to what extent? |
MINGJIE SUN et. al. | iccv | 2021-10-08 |
| 338 | SurfaceNet: Adversarial SVBRDF Estimation From A Single Image Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present SurfaceNet, an approach for estimating spatially-varying bidirectional reflectance distribution function (SVBRDF) material properties from a single image. |
Giuseppe Vecchio; Simone Palazzo; Concetto Spampinato; | iccv | 2021-10-08 |
| 339 | Teacher-Student Adversarial Depth Hallucination To Improve Face Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the Teacher-Student Generative Adversarial Network (TS-GAN) to generate depth images from single RGB images in order to boost the performance of face recognition systems. |
Hardik Uppal; Alireza Sepas-Moghaddam; Michael Greenspan; Ali Etemad; | iccv | 2021-10-08 |
| 340 | InSeGAN: A Generative Approach to Segmenting Identical Instances in Depth Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present InSeGAN an unsupervised 3D generative adversarial network (GAN) for segmenting (nearly) identical instances of rigid objects in depth images. |
Anoop Cherian; Goncalo Dias Pais; Siddarth Jain; Tim K. Marks; Alan Sullivan; | iccv | 2021-10-08 |
| 341 | CODEs: Chamfer Out-of-Distribution Examples Against Overconfidence Issue Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes the Chamfer OOD examples (CODEs), whose distribution is close to that of in-distribution samples, and thus could be utilized to alleviate the OOD overconfidence issue effectively by suppressing predictions on them. |
KEKE TANG et. al. | iccv | 2021-10-08 |
| 342 | Omni-GAN: On The Secrets of CGANs and Beyond Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents Omni-GAN, a variant of cGAN that reveals the devil in designing a proper discriminator for training the model. |
Peng Zhou; Lingxi Xie; Bingbing Ni; Cong Geng; Qi Tian; | iccv | 2021-10-08 |
| 343 | Robustness and Generalization Via Generative Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Generative Adversarial Training, an approach to simultaneously improve the model’s generalization and robustness to unseen adversarial attacks. |
Omid Poursaeed; Tianxing Jiang; Harry Yang; Serge Belongie; Ser-Nam Lim; | iccv | 2021-10-08 |
| 344 | Online Multi-Granularity Distillation for GAN Compression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this issue, we propose a novel online multi-granularity distillation (OMGD) scheme to obtain lightweight GANs, which contributes to generating high-fidelity images with low computational demands. |
Yuxi Ren; Jie Wu; Xuefeng Xiao; Jianchao Yang; | iccv | 2021-10-08 |
| 345 | Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take one further step in this direction and propose a conditional generative adversarial network (GAN) that generates images with a defined number of objects from given classes. |
Amrutha Saseendran; Kathrin Skubch; Margret Keuper; | iccv | 2021-10-08 |
| 346 | RECALL: Replay-Based Continual Learning in Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We tackle these issues by recreating no longer available data for the old classes and outlining a content inpainting scheme on the background class. |
Andrea Maracani; Umberto Michieli; Marco Toldo; Pietro Zanuttigh; | iccv | 2021-10-08 |
| 347 | Towards Discovery and Attribution of Open-World GAN Generated Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an iterative algorithm for discovering images generated from previously unseen GANs by exploiting the fact that all GANs leave distinct fingerprints on their generated images. |
Sharath Girish; Saksham Suri; Sai Saketh Rambhatla; Abhinav Shrivastava; | iccv | 2021-10-08 |
| 348 | LatentCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a contrastive learning-based approach to discover semantic directions in the latent space of pre-trained GANs in a self-supervised manner. |
Oguz Kaan Yuksel; Enis Simsar; Ezgi Gulperi Er; Pinar Yanardag; | iccv | 2021-10-08 |
| 349 | Naturalistic Physical Adversarial Patch for Object Detectors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a method to craft physical adversarial patches for object detectors by leveraging the learned image manifold of a pretrained generative adversarial network (GAN) (e.g., BigGAN and StyleGAN) upon real-world images. |
YU-CHIH-TUAN HU et. al. | iccv | 2021-10-08 |
| 350 | Indoor Scene Generation From A Collection of Semantic-Segmented Depth Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a method for creating 3D indoor scenes with a generative model learned from a collection of semantic-segmented depth images captured from different unknown scenes. |
Ming-Jia Yang; Yu-Xiao Guo; Bin Zhou; Xin Tong; | iccv | 2021-10-08 |
| 351 | Learning Causal Representation for Training Cross-Domain Pose Estimator Via Generative Interventions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take a step towards training robust models for cross-domain pose estimation task, which brings together ideas from causal representation learning and generative adversarial networks. |
XIHENG ZHANG et. al. | iccv | 2021-10-08 |
| 352 | MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a multi-generator model for pedestrian trajectory prediction. |
Patrick Dendorfer; Sven Elflein; Laura Leal-Taixe; | iccv | 2021-10-08 |
| 353 | Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an unsupervised approach to conduct the pose transfer between any arbitrate given 3D meshes. |
HAOYU CHEN et. al. | iccv | 2021-10-08 |
| 354 | Unsupervised Segmentation Incorporating Shape Prior Via Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an image segmentation algorithm that is developed in an unsupervised deep learning framework. |
Dahye Kim; Byung-Woo Hong; | iccv | 2021-10-08 |
| 355 | Generative Compositional Augmentations for Scene Graph Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To that end, we propose a method to synthesize rare yet plausible scene graphs by perturbing real ones. |
BORIS KNYAZEV et. al. | iccv | 2021-10-08 |
| 356 | Reality Transform Adversarial Generators for Image Splicing Forgery Detection and Localization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We view this retouching process as image style transfer and then proposed the fake-to-realistic transformation generator GT. |
Xiuli Bi; Zhipeng Zhang; Bin Xiao; | iccv | 2021-10-08 |
| 357 | Detail Me More: Improving GAN’s Photo-Realism of Complex Scenes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the present work, we propose to add a "broker" module in Generative Adversarial Networks (GAN) to solve this problem. |
Raghudeep Gadde; Qianli Feng; Aleix M. Martinez; | iccv | 2021-10-08 |
| 358 | Towards Vivid and Diverse Image Colorization With Generative Color Prior Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim at recovering vivid colors by leveraging the rich and diverse color priors encapsulated in a pretrained Generative Adversarial Networks (GAN). |
YANZE WU et. al. | iccv | 2021-10-08 |
| 359 | Learning To Remove Refractive Distortions From Underwater Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we present the distortion-guided network (DG-Net) for restoring distortion-free underwater images. |
Simron Thapa; Nianyi Li; Jinwei Ye; | iccv | 2021-10-08 |
| 360 | WaveFill: A Wavelet-Based Generation Network for Image Inpainting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents WaveFill, a wavelet-based inpainting network that decomposes images into multiple frequency bands and fills the missing regions in each frequency band separately and explicitly. |
YINGCHEN YU et. al. | iccv | 2021-10-08 |
| 361 | Collaging Class-specific GANs for Semantic Image Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new approach for high resolution semantic image synthesis. |
YUHENG LI et. al. | arxiv-cs.CV | 2021-10-08 |
| 362 | F-Drop&Match: GANs With A Dead Zone in The High-Frequency Domain Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this issue, we introduce two novel training techniques called frequency dropping (F-Drop) and frequency matching (F-Match). |
Shin’ya Yamaguchi; Sekitoshi Kanai; | iccv | 2021-10-08 |
| 363 | ReStyle: A Residual-Based StyleGAN Encoder Via Iterative Refinement IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recognizing the limitations of current inversion approaches, in this work we present a novel inversion scheme that extends current encoder-based inversion methods by introducing an iterative refinement mechanism. |
Yuval Alaluf; Or Patashnik; Daniel Cohen-Or; | iccv | 2021-10-08 |
| 364 | Unsupervised Image Generation With Infinite Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new unsupervised non-parametric method named mixture of infinite conditional GANs or MIC-GANs, to tackle several GAN issues together, aiming for image generation with parsimonious prior knowledge. |
Hui Ying; He Wang; Tianjia Shao; Yin Yang; Kun Zhou; | iccv | 2021-10-08 |
| 365 | FACIAL: Synthesizing Dynamic Talking Face With Implicit Attribute Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a talking face generation method that takes an audio signal as input and a short target video clip as reference, and synthesizes a photo-realistic video of the target face with natural lip motions, head poses, and eye blinks that are in-sync with the input audio signal. |
CHENXU ZHANG et. al. | iccv | 2021-10-08 |
| 366 | Dual Projection Generative Adversarial Networks for Conditional Image Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by this intuition, we propose a Dual Projection GAN (P2GAN) model that learns to balance between data matching and label matching . |
LIGONG HAN et. al. | iccv | 2021-10-08 |
| 367 | Generative Adversarial Registration for Improved Conditional Deformable Templates Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We reformulate deformable registration and conditional template estimation as an adversarial game wherein we encourage realism in the moved templates with a generative adversarial registration framework conditioned on flexible image covariates. |
Neel Dey; Mengwei Ren; Adrian V. Dalca; Guido Gerig; | iccv | 2021-10-08 |
| 368 | Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel unpaired SR training framework based on feature distribution alignment, with which we can obtain degradation-indistinguishable feature maps and then map them to HR images. |
Wei Wang; Haochen Zhang; Zehuan Yuan; Changhu Wang; | iccv | 2021-10-08 |
| 369 | Instance Similarity Learning for Unsupervised Feature Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation. |
Ziwei Wang; Yunsong Wang; Ziyi Wu; Jiwen Lu; Jie Zhou; | iccv | 2021-10-08 |
| 370 | EigenGAN: Layer-Wise Eigen-Learning for GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes EigenGAN which is able to unsupervisedly mine interpretable and controllable dimensions from different generator layers. |
Zhenliang He; Meina Kan; Shiguang Shan; | iccv | 2021-10-08 |
| 371 | DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a Dynamic ResBlock Generative Adversarial Network (DRB-GAN) for artistic style transfer. |
Wenju Xu; Chengjiang Long; Ruisheng Wang; Guanghui Wang; | iccv | 2021-10-08 |
| 372 | Painting From Part Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the challenge of taking full advantage of both information from local domain (part) and knowledge from global domain (dataset), we propose a novel part-painting method according to the observations of relationship between part and whole, which consists of three stages: part-noise restarting, part-feature repainting, and part-patch refining, to paint the whole image by leveraging both feature-level and patch-level part as well as powerful representation ability of generative adversarial network. |
DONGSHENG GUO et. al. | iccv | 2021-10-08 |
| 373 | Game Theory for Adversarial Attacks and Defenses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we are on the defensive side to apply game-theoretic approaches on defending against attacks. |
Shorya Sharma; | arxiv-cs.LG | 2021-10-08 |
| 374 | Explainability-Aware One Point Attack for Point Cloud Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose two adversarial methods: One Point Attack (OPA) and Critical Traversal Attack (CTA), which incorporate the explainability technologies and aim to explore the intrinsic operating principle of point cloud networks and their sensitivity against critical points perturbations. |
Hanxiao Tan; Helena Kotthaus; | arxiv-cs.CV | 2021-10-08 |
| 375 | Minimal Adversarial Examples for Deep Learning on 3D Point Clouds Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore adversarial attacks for point cloud-based neural networks. |
Jaeyeon Kim; Binh-Son Hua; Thanh Nguyen; Sai-Kit Yeung; | iccv | 2021-10-08 |
| 376 | Adversarial Example Detection Using Latent Neighborhood Graph Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the first graph-based adversarial detection method that constructs a Latent Neighborhood Graph (LNG) around an input example to determine if the input example is adversarial. |
AHMED ABUSNAINA et. al. | iccv | 2021-10-08 |
| 377 | Towards Understanding The Generative Capability of Adversarially Robust Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recently, some works found an interesting phenomenon that adversarially robust classifiers can generate good images comparable to generative models. We investigate this phenomenon from an energy perspective and provide a novel explanation. |
YAO ZHU et. al. | iccv | 2021-10-08 |
| 378 | Adversarial Attack on Deep Cross-Modal Hamming Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an effective Adversarial Attack on Deep Cross-Modal Hamming Retrieval, dubbed AACH, which fools a target deep CMHR model in a black-box setting. |
Chao Li; Shangqian Gao; Cheng Deng; Wei Liu; Heng Huang; | iccv | 2021-10-08 |
| 379 | Towards Robustness of Deep Neural Networks Via Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the observation that adversarial examples often lie outside the natural image data manifold and the intrinsic dimension of image data is much smaller than its pixel space dimension, we propose to embed high-dimensional input images into a low-dimensional space and apply regularization on the embedding space to push the adversarial examples back to the manifold. |
YAO LI et. al. | iccv | 2021-10-08 |
| 380 | Adversarial Attacks Are Reversible With Natural Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We find that images contain intrinsic structure that enables the reversal of many adversarial attacks. |
Chengzhi Mao; Mia Chiquier; Hao Wang; Junfeng Yang; Carl Vondrick; | iccv | 2021-10-08 |
| 381 | AdvRush: Searching for Adversarially Robust Neural Architectures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take a step beyond training of the weight parameters and consider the problem of designing an adversarially robust neural architecture with high intrinsic robustness. |
Jisoo Mok; Byunggook Na; Hyeokjun Choe; Sungroh Yoon; | iccv | 2021-10-08 |
| 382 | On The Robustness of Vision Transformers to Adversarial Examples IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the robustness of Vision Transformers to adversarial examples. |
Kaleel Mahmood; Rigel Mahmood; Marten van Dijk; | iccv | 2021-10-08 |
| 383 | Low Curvature Activations Reduce Overfitting in Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that the observed generalization gap is closely related to the choice of the activation function. |
Vasu Singla; Sahil Singla; Soheil Feizi; David Jacobs; | iccv | 2021-10-08 |
| 384 | Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For the first time, we comprehensively evaluate the robustness of existing UDA methods and propose a robust UDA approach. |
JINYU YANG et. al. | iccv | 2021-10-08 |
| 385 | On Generating Transferable Targeted Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new generative approach for highly transferable targeted perturbations (\ours). |
Muzammal Naseer; Salman Khan; Munawar Hayat; Fahad Shahbaz Khan; Fatih Porikli; | iccv | 2021-10-08 |
| 386 | Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the observation that language descriptions of natural scene images have already captured the object co-occurrence relationships that can be learned by a language model, we develop a novel approach to perform context consistency checks using such language models. |
MINGJUN YIN et. al. | iccv | 2021-10-08 |
| 387 | AGKD-BML: Defense Against Adversarial Attack By Attention Guided Knowledge Distillation and Bi-Directional Metric Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel adversarial training-based model by Attention Guided Knowledge Distillation and Bi-directional Metric Learning (AGKD-BML). |
Hong Wang; Yuefan Deng; Shinjae Yoo; Haibin Ling; Yuewei Lin; | iccv | 2021-10-08 |
| 388 | Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a dynamic divide-and-conquer adversarial training (DDC-AT) strategy to enhance the defense effect, by setting additional branches in the target model during training, and dealing with pixels with diverse properties towards adversarial perturbation. |
Xiaogang Xu; Hengshuang Zhao; Jiaya Jia; | iccv | 2021-10-08 |
| 389 | Defending Against Universal Adversarial Patches By Clipping Feature Norms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we empirically reveal and mathematically explain that the universal adversarial patches usually lead to deep feature vectors with very large norms in popular CNNs. |
CHENG YU et. al. | iccv | 2021-10-08 |
| 390 | Meta-Attack: Class-Agnostic and Model-Agnostic Physical Adversarial Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle these issues, we propose a class-agnostic and model-agnostic physical adversarial attack model (Meta-Attack), which is able to not only generate robust physical adversarial examples by simulating color and shape distortions, but also generalize to attacking novel images and novel DNN models by accessing a few digital and physical images. |
Weiwei Feng; Baoyuan Wu; Tianzhu Zhang; Yong Zhang; Yongdong Zhang; | iccv | 2021-10-08 |
| 391 | Collaborative and Adversarial Learning of Focused and Dispersive Representations for Semi-Supervised Polyp Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel semi-supervised polyp segmentation via collaborative and adversarial learning of focused and dispersive representations learning model, where focused and dispersive extraction module are used to deal with the diversity of location and shape of polyps. |
Huisi Wu; Guilian Chen; Zhenkun Wen; Jing Qin; | iccv | 2021-10-08 |
| 392 | AdvDrop: Adversarial Attack to DNNs By Dropping Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate this issue from an adversarial viewpoint: will the performance of DNNs decrease even for the images only losing a little information? |
RANJIE DUAN et. al. | iccv | 2021-10-08 |
| 393 | Multi-Expert Adversarial Attack Detection in Person Re-Identification Using Context Inconsistency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a Multi-Expert Adversarial Attack Detection (MEAAD) approach to achieve this goal by checking context inconsistency, which is suitable for any DNNs-based ReID systems. |
Xueping Wang; Shasha Li; Min Liu; Yaonan Wang; Amit K. Roy-Chowdhury; | iccv | 2021-10-08 |
| 394 | Removing Adversarial Noise in Class Activation Feature Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this problem, in this paper, we propose to remove adversarial noise by implementing a self-supervised adversarial training mechanism in a class activation feature space. |
DAWEI ZHOU et. al. | iccv | 2021-10-08 |
| 395 | Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we leverage the concept of knowledge distillation to improve the robustness of small models by distilling from adversarially trained large models. |
Bojia Zi; Shihao Zhao; Xingjun Ma; Yu-Gang Jiang; | iccv | 2021-10-08 |
| 396 | Dyn-Backdoor: Backdoor Attack on Dynamic Link Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the issue, we propose a novel backdoor attack framework on DLP, denoted as Dyn-Backdoor. |
JINYIN CHEN et. al. | arxiv-cs.AI | 2021-10-07 |
| 397 | StyleGAN-induced Data-driven Regularization for Inverse Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our proposed approach, which we refer to as learned Bayesian reconstruction with generative models (L-BRGM), entails joint optimization over the style-code and the input latent code, and enhances the expressive power of a pre-trained StyleGAN2 generator by allowing the style-codes to be different for different generator layers. |
Arthur Conmy; Subhadip Mukherjee; Carola-Bibiane Schönlieb; | arxiv-cs.CV | 2021-10-07 |
| 398 | Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address this gap via a comprehensive investigation on the impact of network width and depth on the robustness of adversarially trained DNNs. |
HANXUN HUANG et. al. | arxiv-cs.LG | 2021-10-07 |
| 399 | One Thing to Fool Them All: Generating Interpretable, Universal, and Physically-Realizable Adversarial Features Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To study feature-class associations in networks and better understand the real-world threats they face, we develop feature-level adversarial perturbations using deep image generators and a novel optimization objective. |
Stephen Casper; Max Nadeau; Gabriel Kreiman; | arxiv-cs.LG | 2021-10-07 |
| 400 | SDA-GAN: Unsupervised Image Translation Using Spectral Domain Attention-Guided Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work introduced a novel GAN architecture for unsupervised image translation on the task of face style transform. |
Qizhou Wang; Maksim Makarenko; | arxiv-cs.CV | 2021-10-06 |
| 401 | Adversarial Attacks on Spiking Convolutional Networks for Event-based Vision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show how white-box adversarial attack algorithms can be adapted to the discrete and sparse nature of event-based visual data, and to the continuous-time setting of spiking neural networks. |
Julian Büchel; Gregor Lenz; Yalun Hu; Sadique Sheik; Martino Sorbaro; | arxiv-cs.CV | 2021-10-06 |
| 402 | Reversible Attack Based on Local Visual Adversarial Perturbation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new method for generating reversible adversarial examples based on local visual adversarial perturbation. |
Li Chen; Shaowei Zhu; Zhaoxia Yin; | arxiv-cs.CV | 2021-10-06 |
| 403 | Adversarial Attacks on Machinery Fault Diagnosis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For fault diagnosis problems, in this paper, we reformulate various adversarial attacks and intensively investigate them under untargeted and targeted conditions. |
Jiahao Chen; Diqun Yan; | arxiv-cs.CR | 2021-10-06 |
| 404 | Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Overall, we find that the two architectures, especially ViT, are more robust than their CNN models. |
Philipp Benz; Soomin Ham; Chaoning Zhang; Adil Karjauv; In So Kweon; | arxiv-cs.CV | 2021-10-06 |
| 405 | Solve Minimax Optimization By Anderson Acceleration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new minimax optimization framework, GDA-AM, that views the GDAdynamics as a fixed-point iteration and solves it using Anderson Mixing to con-verge to the local minimax. |
Huan He; Shifan Zhao; Yuanzhe Xi; Joyce C Ho; Yousef Saad; | arxiv-cs.LG | 2021-10-05 |
| 406 | Voice Aging with Audio-Visual Style Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we apply a similar approach to age a speaker’s voice, referred to as voice aging. |
Justin Wilson; Sunyeong Park; Seunghye J. Wilson; Ming C. Lin; | arxiv-cs.SD | 2021-10-05 |
| 407 | Hypernetworks for Continual Semi-Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this in a continual learning setting, we propose a framework for semi-supervised continual learning called Meta-Consolidation for Continual Semi-Supervised Learning (MCSSL). |
Dhanajit Brahma; Vinay Kumar Verma; Piyush Rai; | arxiv-cs.LG | 2021-10-05 |
| 408 | Frequency Aware Face Hallucination Generative Adversarial Network with Semantic Structural Constraint Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address the issue of face hallucination. |
Shailza Sharma; Abhinav Dhall; Vinay Kumar; | arxiv-cs.CV | 2021-10-05 |
| 409 | An Improved Genetic Algorithm and Its Application in Neural Network Adversarial Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a novel improved genetic algorithm is proposed by improving the crossover and mutation operation of the simple genetic algorithm, and it is verified by four test functions. |
Dingming Yang; Zeyu Yu; Hongqiang Yuan; Yanrong Cui; | arxiv-cs.NE | 2021-10-05 |
| 410 | Adversarial Defenses Via A Mixture of Generators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method to transform the adversarial input data through a mixture of generators in order to recover the correct class obfuscated by the adversarial attack. |
Maciej Żelaszczyk; Jacek Mańdziuk; | arxiv-cs.LG | 2021-10-05 |
| 411 | GenCo: Generative Co-training for Generative Adversarial Networks with Limited Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Several prior studies address this issue by expanding the distribution of the limited training data via massive and hand-crafted data augmentation. |
KAIWEN CUI et. al. | arxiv-cs.CV | 2021-10-04 |
| 412 | Enhance Images As You Like with Unpaired Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, we propose a lightweight one-path conditional generative adversarial network (cGAN) to learn a one-to-many relation from low-light to normal-light image space, given only sets of low- and normal-light training images without any correspondence. |
Xiaopeng Sun; Muxingzi Li; Tianyu He; Lubin Fan; | arxiv-cs.CV | 2021-10-03 |
| 413 | Automated Seed Quality Testing System Using GAN & Active Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel computer vision-based system for automating this process. |
Sandeep Nagar; Prateek Pani; Raj Nair; Girish Varma; | arxiv-cs.CV | 2021-10-02 |
| 414 | Learning from Demonstrations for Autonomous Soft-tissue Retraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an LfD methodology based on Generative Adversarial Imitation Learning (GAIL) that is built on a Deep Reinforcement Learning (DRL) setting. |
AMEYA PORE et. al. | arxiv-cs.RO | 2021-10-01 |
| 415 | Inverse Airfoil Design Method for Generating Varieties of Smooth Airfoils Using Conditional WGAN-gp Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we employed conditional Wasserstein GAN with gradient penalty (CWGAN-GP) to generate airfoil shapes, and the obtained shapes are as smooth as those obtained using smoothing methods. |
Kazuo Yonekura; Nozomu Miyamoto; Katsuyuki Suzuki; | arxiv-cs.LG | 2021-10-01 |
| 416 | AffectGAN: Affect-Based Generative Art Driven By Semantics Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a novel method for generating artistic images that express particular affective states. |
Theodoros Galanos; Antonios Liapis; Georgios N. Yannakakis; | arxiv-cs.CV | 2021-09-30 |
| 417 | SPATE-GAN: Improved Generative Modeling of Dynamic Spatio-Temporal Patterns with An Autoregressive Embedding Loss Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose a novel loss objective combined with COT-GAN based on an autoregressive embedding to reinforce the learning of spatio-temporal dynamics. |
Konstantin Klemmer; Tianlin Xu; Beatrice Acciaio; Daniel B. Neill; | arxiv-cs.LG | 2021-09-30 |
| 418 | Latent Network Embedding Via Adversarial Auto-encoders Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a latent network embedding model based on adversarial graph auto-encoders. |
Minglong Lei; Yong Shi; Lingfeng Niu; | arxiv-cs.LG | 2021-09-30 |
| 419 | You Cannot Easily Catch Me: A Low-Detectable Adversarial Patch for Object Detectors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For such probes, we came up with a novel approach, a Low-Detectable Adversarial Patch, which attacks an object detector with small and texture-consistent adversarial patches, making these adversaries less likely to be recognized. |
Zijian Zhu; Hang Su; Chang Liu; Wenzhao Xiang; Shibao Zheng; | arxiv-cs.CV | 2021-09-30 |
| 420 | Semi-Supervised Adversarial Discriminative Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an improved adversarial domain adaptation method called Semi-Supervised Adversarial Discriminative Domain Adaptation (SADDA), which can overcome the limitation of other domain adaptation. |
Thai-Vu Nguyen; Anh Nguyen; Bac Le; | arxiv-cs.CV | 2021-09-27 |
| 421 | GANG-MAM: GAN Based EnGine for Modifying Android Malware Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a system that produces a feature vector for making an Android malware strongly evasive and then modify the malicious program accordingly. |
Renjith G; Sonia Laudanna; Aji S; Corrado Aaron Visaggio; Vinod P; | arxiv-cs.CR | 2021-09-27 |
| 422 | IGAN: Inferent and Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: I present IGAN (Inferent Generative Adversarial Networks), a neural architecture that learns both a generative and an inference model on a complex high dimensional data distribution, i.e. a bidirectional mapping between data samples and a simpler low-dimensional latent space. |
Dr. Luc Vignaud; | arxiv-cs.LG | 2021-09-27 |
| 423 | Query-based Adversarial Attacks on Graph with Fake Nodes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we proposed Cluster Attack, a novel adversarial attack by introducing a set of fake nodes to the original graph which can mislead the classification on certain victim nodes. |
Zhengyi Wang; Zhongkai Hao; Hang Su; Jun Zhu; | arxiv-cs.LG | 2021-09-27 |
| 424 | Audio-to-Image Cross-Modal Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we consider VAEs in an adversarial training framework in order to ensure more variability in the generated data and find that there is a trade-off between the consistency and diversity of the generated images – this trade-off can be governed by scaling the reconstruction loss up or down, respectively. |
Maciej Żelaszczyk; Jacek Mańdziuk; | arxiv-cs.MM | 2021-09-27 |
| 425 | A Novel Network Training Approach for Open Set Image Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel approach for mining a Known UnknownTrainer or KUT set and design a deep OSR Network (OSRNet) to harness this dataset. |
Md Tahmid Hossaina; Shyh Wei Teng; Guojun Lu; Ferdous Sohel; | arxiv-cs.CV | 2021-09-26 |
| 426 | Structure-Preserving Image Super-Resolution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a structure-preserving super-resolution (SPSR) method to alleviate the above issue while maintaining the merits of GAN-based methods to generate perceptual-pleasant details. |
Cheng Ma; Yongming Rao; Jiwen Lu; Jie Zhou; | arxiv-cs.CV | 2021-09-26 |
| 427 | Generalized Multiscale Feature Extraction for Remaining Useful Life Prediction of Bearings with Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose a novel generalized multiscale feature extraction method with generative adversarial networks. |
Sungho Suh; Paul Lukowicz; Yong Oh Lee; | arxiv-cs.LG | 2021-09-26 |
| 428 | Logo Generation Using Regional Features: A Faster R-CNN Approach to Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we introduce Local Logo Generative Adversarial Network (LL-GAN) that uses regional features extracted from Faster R-CNN for logo generation. |
Aram Ter-Sarkisov; Eduardo Alonso; | arxiv-cs.CV | 2021-09-26 |
| 429 | Two Souls in An Adversarial Image: Towards Universal Adversarial Example Detection Using Multi-view Inconsistency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel multi-view adversarial image detector, namely Argos, based on a novel observation. |
Sohaib Kiani; Sana Awan; Chao Lan; Fengjun Li; Bo Luo; | arxiv-cs.CV | 2021-09-25 |
| 430 | Fine-Grained Image Generation from Bangla Text Description Using Attentional Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Considering that, we propose Bangla Attentional Generative Adversarial Network (AttnGAN) that allows intensified, multi-stage processing for high-resolution Bangla text-to-image generation. |
Md Aminul Haque Palash; Md Abdullah Al Nasim; Aditi Dhali; Faria Afrin; | arxiv-cs.CV | 2021-09-24 |
| 431 | Learning Generative Deception Strategies in Combinatorial Masking Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel game-theoretic model of the resulting defender-attacker interaction, where the defender chooses a subset of attributes to mask, while the attacker responds by choosing an exploit to execute. |
Junlin Wu; Charles Kamhoua; Murat Kantarcioglu; Yevgeniy Vorobeychik; | arxiv-cs.GT | 2021-09-23 |
| 432 | Exploring Adversarial Examples for Efficient Active Learning in Machine Learning Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Through analyzing various representative classifiers such as k-NN classifiers, kernel methods as well as deep neural networks, we establish a theoretical foundation for the observation. |
Honggang Yu; Shihfeng Zeng; Teng Zhang; Ing-Chao Lin; Yier Jin; | arxiv-cs.LG | 2021-09-22 |
| 433 | PECAM: Privacy-enhanced Video Streaming and Analytics Via Securely-reversible Transformation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a VSA privacy enhancement system (PECAM), which addresses the above challenge with no change in the VSA back-end. |
HAO WU et. al. | mobicom | 2021-09-21 |
| 434 | Scenario Generation for Market Risk Models Using Generative Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this research, we show how to expand existing approaches of generative adversarial networks (GANs) being used as economic scenario generators (ESG) to a whole internal model – with enough risk factors to model the full band-width of investments for an insurance company and for a one year horizon as required in Solvency 2. |
Solveig Flaig; Gero Junike; | arxiv-cs.LG | 2021-09-21 |
| 435 | Generating Compositional Color Representations from Text Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel dataset curation pipeline from existing public sources. |
PARIDHI MAHESHWARI et. al. | arxiv-cs.CV | 2021-09-21 |
| 436 | 3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that training with adversarial samples can improve the performance of neural networks on 3D point cloud completion tasks. |
Mengxi Wu; Hao Huang; Yi Fang; | arxiv-cs.CV | 2021-09-21 |
| 437 | Unsupervised Cycle-consistent Generative Adversarial Networks for Pan-sharpening Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an unsupervised generative adversarial framework that learns from the full-scale images without the ground truths to alleviate this problem. |
Huanyu Zhou; Qingjie Liu; Yunhong Wang; | arxiv-cs.CV | 2021-09-20 |
| 438 | FreeStyleGAN: Free-view Editable Portrait Rendering with The Camera Manifold Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In our solution, we use a few images of a face to perform 3D reconstruction, and we introduce the notion of the GAN camera manifold, the key element allowing us to precisely define the range of images that the GAN can reproduce in a stable manner. |
Thomas Leimkühler; George Drettakis; | arxiv-cs.GR | 2021-09-20 |
| 439 | Modeling Adversarial Noise for Adversarial Defense Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the fact that adversarial noise contains well-generalizing features and that the relationship between adversarial data and natural data can help infer natural data and make reliable predictions, in this paper, we study to model adversarial noise by learning the transition relationship between adversarial labels (i.e. the flipped labels used to generate adversarial data) and natural labels (i.e. the ground truth labels of the natural data). |
Dawei Zhou; Nannan Wang; Bo Han; Tongliang Liu; | arxiv-cs.LG | 2021-09-20 |
| 440 | ComicGAN: Text-to-Comic Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe an in-depth empirical study of the technical difficulties of comic generation using GAN’s. |
Ben Proven-Bessel; Zilong Zhao; Lydia Chen; | arxiv-cs.CV | 2021-09-19 |
| 441 | On The Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore the design of robust DNNs through the amalgamation of adversarial training and the intrinsic robustness offered by NVM crossbar-based analog hardware. |
Deboleena Roy; Chun Tao; Indranil Chakraborty; Kaushik Roy; | arxiv-cs.LG | 2021-09-19 |
| 442 | Hybrid Data Augmentation and Deep Attention-based Dilated Convolutional-Recurrent Neural Networks for Speech Emotion Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this article, we investigate hybrid data augmentation (HDA) methods to generate and balance data based on traditional and generative adversarial networks (GAN) methods. |
Nhat Truong Pham; Duc Ngoc Minh Dang; Sy Dzung Nguyen; | arxiv-cs.SD | 2021-09-18 |
| 443 | Manifold-preserved GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address such open challenges, this paper proposes Manifold-preserved GANs (MaF-GANs), which generalize Wasserstein GANs into high-dimensional form. |
HAOZHE LIU et. al. | arxiv-cs.CV | 2021-09-18 |
| 444 | Harnessing Optoelectronic Noises in A Photonic Generative Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we demonstrate a photonic generative network as a part of a generative adversarial network (GAN). |
CHANGMING WU et. al. | arxiv-cs.ET | 2021-09-17 |
| 445 | WiSoSuper: Benchmarking Super-Resolution Methods on Wind and Solar Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We provide a thorough and extensible benchmark of leading deep learning-based super-resolution techniques, including the enhanced super-resolution generative adversarial network (ESRGAN) and an enhanced deep super-resolution (EDSR) network, on wind and solar data. |
Rupa Kurinchi-Vendhan; Björn Lütjens; Ritwik Gupta; Lucien Werner; Dava Newman; | arxiv-cs.CV | 2021-09-17 |
| 446 | KnowMAN: Weakly Supervised Multinomial Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose KnowMAN, an adversarial scheme that enables to control influence of signals associated with specific labeling functions. |
Luisa März; Ehsaneddin Asgari; Fabienne Braune; Franziska Zimmermann; Benjamin Roth; | arxiv-cs.LG | 2021-09-16 |
| 447 | Simple Post-Training Robustness Using Test Time Augmentations and Random Forest Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Augmented Random Forest (ARF), a simple and easy-to-use strategy for robustifying an existing pretrained DNN without modifying its weights. |
Gilad Cohen; Raja Giryes; | arxiv-cs.CV | 2021-09-16 |
| 448 | New Perspective on Progressive GANs Distillation for One-class Novelty Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, the Generative Adversarial Network based on the Encoder-Decoder-Encoder scheme (EDE-GAN) achieves state-of-the-art performance. |
Zhiwei Zhang; Yu Dong; Hanyu Peng; Shifeng Chen; | arxiv-cs.CV | 2021-09-15 |
| 449 | A Unified Framework for Biphasic Facial Age Translation with Noisy-Semantic Guided Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a unified framework for biphasic facial age translation with noisy-semantic guided generative adversarial networks. |
Muyi Sun; Jian Wang; Yunfan Liu; Qi Li; Zhenan Sun; | arxiv-cs.CV | 2021-09-15 |
| 450 | Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose the Adversarial Mixing Policy (AMP), organized in a min-max-rand formulation, to relax the Locally Linear Constraints in Mixup. |
Guang Liu; Yuzhao Mao; Hailong Huang; Weiguo Gao; Xuan Li; | arxiv-cs.CL | 2021-09-15 |
| 451 | EVAGAN: Evasion Generative Adversarial Network for Low Data Regimes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel GAN design called Evasion Generative Adversarial Network (EVAGAN) that is more suitable for low data regime problems that use oversampling for detection improvement of ML classifiers. |
Rizwan Hamid Randhawa; Nauman Aslam; Mohammad Alauthman; Husnain Rafiq; | arxiv-cs.CR | 2021-09-14 |
| 452 | High-Fidelity GAN Inversion for Image Attribute Editing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel high-fidelity generative adversarial network (GAN) inversion framework that enables attribute editing with image-specific details well-preserved (e.g., background, appearance and illumination). |
Tengfei Wang; Yong Zhang; Yanbo Fan; Jue Wang; Qifeng Chen; | arxiv-cs.CV | 2021-09-14 |
| 453 | Conditional MoCoGAN for Zero-Shot Video Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a conditional generative adversarial network (GAN) model for zero-shot video generation. |
Shun Kimura; Kazuhiko Kawamoto; | arxiv-cs.CV | 2021-09-13 |
| 454 | Evolving Architectures with Gradient Misalignment Toward Low Adversarial Transferability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we address this problem from a novel perspective through investigating the contribution of the network architecture to transferability. |
Kevin Richard G. Operiano; Wanchalerm Pora; Hitoshi Iba; Hiroshi Kera; | arxiv-cs.CV | 2021-09-13 |
| 455 | Improving Robustness of Adversarial Attacks Using An Affine-Invariant Gradient Estimator Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose an affine-invariant adversarial attack which can consistently construct adversarial examples robust over a distribution of affine transformation. |
Wenzhao Xiang; Hang Su; Chang Liu; Yandong Guo; Shibao Zheng; | arxiv-cs.CV | 2021-09-13 |
| 456 | How to Select One Among All? An Extensive Empirical Study Towards The Robustness of Knowledge Distillation in Natural Language Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a framework to assess the adversarial robustness of multiple KD algorithms. |
TIANDA LI et. al. | arxiv-cs.CL | 2021-09-13 |
| 457 | Randomized Substitution and Vote for Textual Adversarial Example Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we treat the optimization process for synonym substitution based textual adversarial attacks as a specific sequence of word replacement, in which each word mutually influences other words. |
Xiaosen Wang; Yifeng Xiong; Kun He; | arxiv-cs.CL | 2021-09-13 |
| 458 | PAT: Pseudo-Adversarial Training For Detecting Adversarial Videos Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel yet simple algorithm called Pseudo-Adversarial Training (PAT), to detect the adversarial frames in a video without requiring knowledge of the attack. |
Nupur Thakur; Baoxin Li; | arxiv-cs.CV | 2021-09-13 |
| 459 | MSGDD-cGAN: Multi-Scale Gradients Dual Discriminator Conditional Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a method called MSGDD-cGAN, which first stabilizes the performance of the cGANs using multi-connections gradients flow. |
Mohammadreza Naderi; Zahra Nabizadeh; Nader Karimi; Shahram Shirani; Shadrokh Samavi; | arxiv-cs.CV | 2021-09-12 |
| 460 | Unsupervised Domain Adaptation for Cross-modality Liver Segmentation Via Joint Adversarial Learning and Self-learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we report a novel unsupervised domain adaptation framework for cross-modality liver segmentation via joint adversarial learning and self-learning. |
Jin Hong; Simon Chun-Ho Yu; Weitian Chen; | arxiv-cs.CV | 2021-09-12 |
| 461 | Conditional Generation of Synthetic Geospatial Images from Pixel-level and Feature-level Inputs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Towards this goal, we present a deep conditional generative model, called VAE-Info-cGAN, that combines a Variational Autoencoder (VAE) with a conditional Information Maximizing Generative Adversarial Network (InfoGAN), for synthesizing semantically rich images simultaneously conditioned on a pixel-level condition (PLC) and a macroscopic feature-level condition (FLC). |
Xuerong Xiao; Swetava Ganguli; Vipul Pandey; | arxiv-cs.CV | 2021-09-11 |
| 462 | A Novel Intrinsic Measure of Data Separability Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To quantitatively measure the separability of datasets, we create an intrinsic measure — the Distance-based Separability Index (DSI), which is independent of the classifier model. |
Shuyue Guan; Murray Loew; | arxiv-cs.LG | 2021-09-11 |
| 463 | 2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a 2-in-1 Accelerator, an integrated algorithm-accelerator co-design framework aiming at winning both the adversarial robustness and efficiency of DNN accelerators. |
Yonggan Fu; Yang Zhao; Qixuan Yu; Chaojian Li; Yingyan Lin; | arxiv-cs.LG | 2021-09-11 |
| 464 | Instance-Conditioned GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take inspiration from kernel density estimation techniques and introduce a non-parametric approach to modeling distributions of complex datasets. |
Arantxa Casanova; Marlène Careil; Jakob Verbeek; Michal Drozdzal; Adriana Romero-Soriano; | arxiv-cs.CV | 2021-09-10 |
| 465 | Robust Optimal Classification Trees Against Adversarial Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose ROCT, a collection of methods to train decision trees that are optimally robust against user-specified attack models. |
Daniël Vos; Sicco Verwer; | arxiv-cs.LG | 2021-09-08 |
| 466 | GANSER: A Self-supervised Data Augmentation Framework for EEG-based Emotion Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel data augmentation framework, namely Generative Adversarial Network-based Self-supervised Data Augmentation (GANSER). |
Zhi Zhang; Sheng-hua Zhong; Yan Liu; | arxiv-cs.LG | 2021-09-07 |
| 467 | Brand Label Albedo Extraction of ECommerce Products Using Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present our solution to extract albedo of branded labels for e-commerce products. To this end, we generate a large-scale photo-realistic synthetic data set for albedo extraction followed by training a generative model to translate images with diverse lighting conditions to albedo. |
Suman Sapkota; Manish Juneja; Laurynas Keleras; Pranav Kotwal; Binod Bhattarai; | arxiv-cs.CV | 2021-09-07 |
| 468 | Adversarial Parameter Defense By Multi-Step Risk Minimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce the concept of parameter corruption and propose to leverage the loss change indicators for measuring the flatness of the loss basin and the parameter robustness of neural network parameters. |
ZHIYUAN ZHANG et. al. | arxiv-cs.LG | 2021-09-07 |
| 469 | Robustness and Generalization Via Generative Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present Generative Adversarial Training, an approach to simultaneously improve the model’s generalization to the test set and out-of-domain samples as well as its robustness to unseen adversarial attacks. |
Omid Poursaeed; Tianxing Jiang; Harry Yang; Serge Belongie; SerNam Lim; | arxiv-cs.CV | 2021-09-06 |
| 470 | Machine Learning: Challenges, Limitations, and Compatibility for Audio Restoration Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The project intent is to build a new trained model from voice data to learn features of compression artifacting distortion introduced by data loss from lossy compression and resolution loss with an existing algorithm presented in SEGAN: Speech Enhancement Generative Adversarial Network. |
Owen Casey; Rushit Dave; Naeem Seliya; Evelyn R Sowells Boone; | arxiv-cs.SD | 2021-09-06 |
| 471 | Gradient Normalization for Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. |
Yi-Lun Wu; Hong-Han Shuai; Zhi-Rui Tam; Hong-Yu Chiu; | arxiv-cs.LG | 2021-09-06 |
| 472 | Automated Robustness with Adversarial Training As A Post-Processing Step Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a step towards practical automation, this work explores the efficacy of a simple post processing step in yielding robust deep learning model. |
Ambrish Rawat; Mathieu Sinn; Beat Buesser; | arxiv-cs.LG | 2021-09-06 |
| 473 | Timbre Transfer with Variational Auto Encoding and Cycle-Consistent Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This research project investigates the application of deep learning to timbre transfer, where the timbre of a source audio can be converted to the timbre of a target audio with minimal loss in quality. |
Russell Sammut Bonnici; Charalampos Saitis; Martin Benning; | arxiv-cs.SD | 2021-09-05 |
| 474 | VARGAN: Variance Enforcing Network Enhanced GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new GAN architecture called variance enforcing GAN (VARGAN), which incorporates a third network to introduce diversity in the generated samples. |
Sanaz Mohammadjafari; Mucahit Cevik; Ayse Basar; | arxiv-cs.LG | 2021-09-05 |
| 475 | A Two-stage Complex Network Using Cycle-consistent Generative Adversarial Networks for Speech Enhancement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by the multi-stage learning concept, we propose a novel two-stage denoising system that combines a CycleGAN-based magnitude enhancing network and a subsequent complex spectral refining network in this paper. |
Guochen Yu; Yutian Wang; Hui Wang; Qin Zhang; Chengshi Zheng; | arxiv-cs.SD | 2021-09-05 |
| 476 | Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel distributed training algorithm, partial synchronous stochastic gradient descent (ParSGD), which defends adversarial attacks and/or tolerates Byzantine faults. |
YUSEN WU et. al. | arxiv-cs.CR | 2021-09-05 |
| 477 | Utilizing Adversarial Targeted Attacks to Boost Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel solution by adopting the recently suggested Predictive Normalized Maximum Likelihood. |
Uriya Pesso; Koby Bibas; Meir Feder; | arxiv-cs.CV | 2021-09-04 |
| 478 | FA-GAN: Feature-Aware GAN for Text to Image Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose Feature-Aware Generative Adversarial Network (FA-GAN) to synthesize a high-quality image by integrating two techniques: a self-supervised discriminator and a feature-aware loss. |
Eunyeong Jeon; Kunhee Kim; Daijin Kim; | arxiv-cs.CV | 2021-09-02 |
| 479 | Solving Inverse Problems with Conditional-GAN Prior Via Fast Network-Projected Gradient Descent Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we investigate a network-based projected gradient descent (NPGD) algorithm for measurement-conditional generative models to solve the inverse problem much faster than regular PGD. |
Muhammad Fadli Damara; Gregor Kornhardt; Peter Jung; | arxiv-cs.LG | 2021-09-02 |
| 480 | Transformer Networks for Data Augmentation of Human Physical Activity Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, transformer based generative adversarial networks which have global attention on data, are compared on PAMAP2 and Real World Human Activity Recognition data sets with RGAN. |
Sandeep Ramachandra; Alexander Hoelzemann; Kristof Van Laerhoven; | arxiv-cs.LG | 2021-09-02 |
| 481 | A Synergetic Attack Against Neural Network Classifiers Combining Backdoor and Adversarial Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. |
Guanxiong Liu; Issa Khalil; Abdallah Khreishah; NhatHai Phan; | arxiv-cs.CR | 2021-09-02 |
| 482 | TabFairGAN: Fair Tabular Data Generation with Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Generative Adversarial Network for tabular data generation. |
Amirarsalan Rajabi; Ozlem Ozmen Garibay; | arxiv-cs.LG | 2021-09-01 |
| 483 | Towards Improving Adversarial Training of NLP Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a simple and improved vanilla adversarial training process for NLP models, which we name Attacking to Training (A2T). |
Jin Yong Yoo; Yanjun Qi; | arxiv-cs.CL | 2021-09-01 |
| 484 | Quantization of Generative Adversarial Networks for Efficient Inference: A Methodological Study Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this problem, we perform an extensive experimental study of state-of-art quantization techniques on three diverse GAN architectures, namely StyleGAN, Self-Attention GAN, and CycleGAN. |
Pavel Andreev; Alexander Fritzler; Dmitry Vetrov; | arxiv-cs.AI | 2021-08-31 |
| 485 | An Introduction to Variational Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce the concept of Variational Inference (VI), a popular method in machine learning that uses optimization techniques to estimate complex probability densities. |
Ankush Ganguly; Samuel W. F. Earp; | arxiv-cs.LG | 2021-08-30 |
| 486 | AIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel adversarial iterative pruning method (AIP) for CNNs based on knowledge transfer. |
Jingfei Chang; Yang Lu; Ping Xue; Yiqun Xu; Zhen Wei; | arxiv-cs.CV | 2021-08-30 |
| 487 | Adversarial Example Devastation and Detection on Speech Recognition System By Adding Random Noise Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an algorithm of devastation and detection on adversarial examples that can attack current advanced ASR systems. |
Mingyu Dong; Diqun Yan; Yongkang Gong; Rangding Wang; | arxiv-cs.SD | 2021-08-30 |
| 488 | Investigating Vulnerabilities of Deep Neural Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the effects of adversarial training on the neural policy learned by the agent. |
Ezgi Korkmaz; | arxiv-cs.LG | 2021-08-30 |
| 489 | RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We test our system on three word-similarity benchmarks and a downstream sentence simplification task and achieve the state of the art (CARD-660). |
PEDRO COLON-HERNANDEZ et. al. | arxiv-cs.CL | 2021-08-29 |
| 490 | DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To further enhance the breadth and depth of attack, we propose a novel masked weight adversarial training method called DropAttack, which enhances generalization of model by adding intentionally worst-case adversarial perturbations to both the input and hidden layers in different dimensions and minimize the adversarial risks generated by each layer. |
Shiwen Ni; Jiawen Li; Hung-Yu Kao; | arxiv-cs.LG | 2021-08-29 |
| 491 | Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel stagewise domain adaptation model called RoadDA to address the DS issue in this field. |
Lefei Zhang; Meng Lan; Jing Zhang; Dacheng Tao; | arxiv-cs.CV | 2021-08-28 |
| 492 | Mal2GCN: A Robust Malware Detection Approach Using Deep Graph Convolutional Networks With Non-Negative Weights Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recent studies have shown that in an adversarial environment, machine learning models are vulnerable to adversarial examples, and adversaries can create carefully crafted inputs to fool the models. |
Omid Kargarnovin; Amir Mahdi Sadeghzadeh; Rasool Jalili; | arxiv-cs.CR | 2021-08-27 |
| 493 | Re-using Adversarial Mask Discriminators for Test-time Training Under Distribution Shifts Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we argue that training stable discriminators produces expressive loss functions that we can re-use at inference to detect and \textit{correct} segmentation mistakes. |
Gabriele Valvano; Andrea Leo; Sotirios A. Tsaftaris; | arxiv-cs.CV | 2021-08-26 |
| 494 | Understanding The Logit Distributions of Adversarially-Trained Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We identify three logit characteristics essential to learning adversarial robustness. |
Landan Seguin; Anthony Ndirango; Neeli Mishra; SueYeon Chung; Tyler Lee; | arxiv-cs.LG | 2021-08-26 |
| 495 | Physical Adversarial Attacks on An Aerial Imagery Object Detector Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we demonstrate one of the first efforts on physical adversarial attacks on aerial imagery, whereby adversarial patches were optimised, fabricated and installed on or near target objects (cars) to significantly reduce the efficacy of an object detector applied on overhead images. |
ANDREW DU et. al. | arxiv-cs.CV | 2021-08-26 |
| 496 | A Hierarchical Assessment of Adversarial Severity Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to study the effects of adversarial noise by measuring the Robustness and Severity into a large-scale dataset: iNaturalist-H. |
Guillaume Jeanneret; Juan C Perez; Pablo Arbelaez; | arxiv-cs.LG | 2021-08-26 |
| 497 | XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes two methods to mimic human-drawn colored sketches by utilizing the Contour Drawing Dataset. |
V MANUSHREE et. al. | arxiv-cs.CV | 2021-08-25 |
| 498 | Adversarially Robust One-class Novelty Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a defense strategy that manipulates the latent space of novelty detectors to improve the robustness against adversarial examples. |
Shao-Yuan Lo; Poojan Oza; Vishal M. Patel; | arxiv-cs.CV | 2021-08-25 |
| 499 | Bridged Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we discover that adversarially trained models might have significantly different characteristics in terms of margin and smoothness, even they show similar robustness. |
Hoki Kim; Woojin Lee; Sungyoon Lee; Jaewook Lee; | arxiv-cs.LG | 2021-08-25 |
| 500 | Kryptonite: An Adversarial Attack Using Regional Focus Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel study analyzing the weaknesses in the security of deep learning systems. |
Yogesh Kulkarni; Krisha Bhambani; | arxiv-cs.CR | 2021-08-23 |
| 501 | Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This tutorial aims to introduce the fundamentals of adversarial robustness of deep learning, presenting a well-structured review of up-to-date techniques to assess the vulnerability of various types of deep learning models to adversarial examples. |
Wenjie Ruan; Xinping Yi; Xiaowei Huang; | arxiv-cs.LG | 2021-08-23 |
| 502 | Robustness-via-Synthesis: Robust Training with Generative Adversarial Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study presents a robust training algorithm where the adversarial perturbations are automatically synthesized from a random vector using a generator network. |
Inci M. Baytas; Debayan Deb; | arxiv-cs.CV | 2021-08-22 |
| 503 | Robust Ensembling Network for Unsupervised Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Robust Ensembling Network (REN) for UDA, which applies a robust time ensembling teacher network to learn global information for domain transfer. |
Han Sun; Lei Lin; Ningzhong Liu; Huiyu Zhou; | arxiv-cs.CV | 2021-08-21 |
| 504 | ReGenMorph: Visibly Realistic GAN Generated Face Morphing Attacks By Attack Re-generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents the novel morphing pipeline, ReGenMorph, to eliminate the LMA blending artifacts by using a GAN-based generation, as well as, eliminate the manipulation in the latent space, resulting in visibly realistic morphed images compared to previous works. |
NASER DAMER et. al. | arxiv-cs.CV | 2021-08-20 |
| 505 | Zoom, Enhance! Measuring Surveillance GAN Up-sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we extend the applications of CNNs and GANs to experiment with up-sampling techniques in the domains of security and surveillance. |
Jake Sparkman; Abdalla Al-Ayrot; Utkarsh Contractor; | arxiv-cs.CV | 2021-08-20 |
| 506 | Dual Projection Generative Adversarial Networks for Conditional Image Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that the former directly aligns the class-conditioned fake-and-real data distributions $P(\text{image}|\text{class})$ ({\em data matching}), while the latter aligns data-conditioned class distributions $P(\text{class}|\text{image})$ ({\em label matching}). |
LIGONG HAN et. al. | arxiv-cs.CV | 2021-08-20 |
| 507 | Cascade Watchdog: A Multi-tiered Adversarial Guard for Outlier Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents and empirically evaluates a multi-tiered watchdog, which is developed using GAN generated data, for improved out-of-distribution detection. |
Glauco A. Amigo Galán; Justin Bui; Robert J. Marks; | arxiv-cs.LG | 2021-08-20 |
| 508 | Towards Understanding The Generative Capability of Adversarially Robust Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recently, some works found an interesting phenomenon that adversarially robust classifiers can generate good images comparable to generative models. |
YAO ZHU et. al. | arxiv-cs.LG | 2021-08-20 |
| 509 | Mitigating Greenhouse Gas Emissions Through Generative Adversarial Networks Based Wildfire Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop a deep learning based data augmentation approach for wildfire risk prediction. We build a dataset consisting of diverse features responsible for fire ignition and utilize a conditional tabular generative adversarial network to explore the underlying patterns between the target value of risk levels and all involved features. |
Sifat Chowdhury; Kai Zhu; Yu Zhang; | arxiv-cs.LG | 2021-08-19 |
| 510 | Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study GAIL in both online and offline settings with linear function approximation, where both the transition and reward function are linear in the feature maps. |
Zhihan Liu; Yufeng Zhang; Zuyue Fu; Zhuoran Yang; Zhaoran Wang; | arxiv-cs.LG | 2021-08-19 |
| 511 | ASAT: Adaptively Scaled Adversarial Training in Time Series Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take the first step to introduce adversarial training in time series analysis by taking the finance field as an example. |
ZHIYUAN ZHANG et. al. | arxiv-cs.LG | 2021-08-19 |
| 512 | Pruning in The Face of Adversaries Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: One approach to control the size of neural networks is retrospectively reducing the number of parameters, so-called neural network pruning. |
Florian Merkle; Maximilian Samsinger; Pascal Schöttle; | arxiv-cs.LG | 2021-08-19 |
| 513 | Application of Adversarial Examples to Physical ECG Signals Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work aims to assess the reality and feasibility of the adversarial attack against cardiac diagnosis system powered by machine learning algorithms. |
Taiga Ono; Takeshi Sugawara; Jun Sakuma; Tatsuya Mori; | arxiv-cs.LG | 2021-08-19 |
| 514 | Scarce Data Driven Deep Learning of Drones Via Generalized Data Distribution Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we show how understanding the general distribution of the drone data via a Generative Adversarial Network (GAN) and explaining the missing features using Topological Data Analysis (TDA) – can allow us to acquire missing data to achieve rapid and more accurate learning. |
Chen Li; Schyler C. Sun; Zhuangkun Wei; Antonios Tsourdos; Weisi Guo; | arxiv-cs.CV | 2021-08-18 |
| 515 | MV-TON: Memory-based Video Virtual Try-on Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these challenges, we propose a Memory-based Video virtual Try-On Network (MV-TON), which seamlessly transfers desired clothes to a target person without using any clothing templates and generates high-resolution realistic videos. |
Xiaojing Zhong; Zhonghua Wu; Taizhe Tan; Guosheng Lin; Qingyao Wu; | arxiv-cs.CV | 2021-08-17 |
| 516 | Transferring Knowledge with Attention Distillation for Multi-Domain Image-to-Image Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this reason, in this paper, it is shown how gradient based attentions can be used as knowledge to be conveyed in a teacher-student paradigm for multi-domain image-to-image translat |