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.
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 | Learning High-Dimensional Distributions with Latent Neural Fokker-Planck Kernels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce new techniques to formulate the problem as solving Fokker-Planck equation in a lower-dimensional latent space, aiming to mitigate challenges in high-dimensional data space. |
Yufan Zhou; Changyou Chen; Jinhui Xu; | arxiv-cs.LG | 2021-05-10 |
| 2 | Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we demonstrate how this branch of machine learning can benefit multiple aspects of computer and communication networks, including mobile networks, network analysis, internet of things, physical layer, and cybersecurity. |
HOJJAT NAVIDAN et. al. | arxiv-cs.NI | 2021-05-10 |
| 3 | BIM Hyperreality: Data Synthesis Using BIM and Hyperrealistic Rendering for Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to resolve this bottleneck, we present a concept of a hybrid system using both building information modeling (BIM) and hyperrealistic (photorealistic) rendering to synthesize datasets for training a neural network for building object recognition in photos. |
Mohammad Alawadhi; Wei Yan; | arxiv-cs.LG | 2021-05-10 |
| 4 | Efficiency-driven Hardware Optimization for Adversarially Robust Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show how the bit-errors in the 6T cells of hybrid 6T-8T memories minimize the adversarial perturbations in a DNN. |
Abhiroop Bhattacharjee; Abhishek Moitra; Priyadarshini Panda; | arxiv-cs.LG | 2021-05-09 |
| 5 | Robust Training Using Natural Transformation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To bridge this gap, we present NaTra, an adversarial training scheme that is designed to improve the robustness of image classification algorithms. |
SHUO WANG et. al. | arxiv-cs.CV | 2021-05-09 |
| 6 | Learning Image Attacks Toward Vision Guided Autonomous Vehicles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents an online adversarial machine learning framework that can effectively misguide autonomous vehicles’ missions. |
Hyung-Jin Yoon; Hamid Jafarnejad Sani; Petros Voulgaris; | arxiv-cs.RO | 2021-05-09 |
| 7 | De-Pois: An Attack-Agnostic Defense Against Data Poisoning Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose De-Pois, an attack-agnostic defense against poisoning attacks. |
Jian Chen; Xuxin Zhang; Rui Zhang; Chen Wang; Ling Liu; | arxiv-cs.CR | 2021-05-08 |
| 8 | Stability and Generalization of Stochastic Gradient Methods for Minimax Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a comprehensive generalization analysis of stochastic gradient methods for minimax problems under both convex-concave and nonconvex-nonconcave cases through the lens of algorithmic stability. |
Yunwen Lei; Zhenhuan Yang; Tianbao Yang; Yiming Ying; | arxiv-cs.LG | 2021-05-08 |
| 9 | Self-Supervised Adversarial Example Detection By Disentangled Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We compare our method with the state-of-the-art self-supervised detection methods under different adversarial attacks and different victim models (30 attack settings), and it exhibits better performance in various measurements (AUC, FPR, TPR) for most attacks settings. |
ZHAOXI ZHANG et. al. | arxiv-cs.CV | 2021-05-08 |
| 10 | Unsupervised Remote Sensing Super-Resolution Via Migration Image Prior Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we proposed a new unsupervised learning framework, called MIP, which achieves SR tasks without low/high resolution image pairs. |
JIAMING WANG et. al. | arxiv-cs.CV | 2021-05-07 |
| 11 | Toward Interactive Modulation for Photo-Realistic Image Restoration Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a Controllable Unet Generative Adversarial Network (CUGAN) to generate high-frequency textures in the modulation tasks. |
Haoming Cai; Jingwen He; Qiao Yu; Chao Dong; | arxiv-cs.CV | 2021-05-07 |
| 12 | Uniform Convergence, Adversarial Spheres and A Simple Remedy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Previous work has cast doubt on the general framework of uniform convergence and its ability to explain generalization in neural networks. |
Gregor Bachmann; Seyed-Mohsen Moosavi-Dezfooli; Thomas Hofmann; | arxiv-cs.LG | 2021-05-07 |
| 13 | Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a unified adversarial face generation method – Adv-Makeup, which can realize imperceptible and transferable attack under black-box setting. |
BANGJIE YIN et. al. | arxiv-cs.CV | 2021-05-07 |
| 14 | GANTL: Towards Practical and Real-Time Topology Optimization with Conditional GANs and Transfer Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a deep learning method based on generative adversarial networks for generative design exploration. |
Mohammad Mahdi Behzadi; Horea T. Ilies; | arxiv-cs.LG | 2021-05-06 |
| 15 | Inverting Generative Adversarial Renderer for Face Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a novel Generative Adversarial Renderer (GAR) and propose to tailor its inverted version to the general fitting pipeline, to tackle the above problem. |
Jingtan Piao; Keqiang Sun; KwanYee Lin; Quan Wang; Hongsheng Li; | arxiv-cs.CV | 2021-05-06 |
| 16 | Brain Multigraph Prediction Using Topology-Aware Adversarial Graph Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these limitations, we introduce topology-aware graph GAN architecture (topoGAN), which jointly predicts multiple brain graphs from a single brain graph while preserving the topological structure of each target graph. |
Alaa Bessadok; Mohamed Ali Mahjoub; Islem Rekik; | arxiv-cs.LG | 2021-05-06 |
| 17 | (ASNA) An Attention-based Siamese-Difference Neural Network with Surrogate Ranking Loss Function for Perceptual Image Quality Assessment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper has proposed a convolutional neural network using an extension architecture of the traditional Siamese network so-called Siamese-Difference neural network. |
Seyed Mehdi Ayyoubzadeh; Ali Royat; | arxiv-cs.CV | 2021-05-06 |
| 18 | A Simple and Strong Baseline for Universal Targeted Attacks on Siamese Visual Tracking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show the existence of universal perturbations that can enable the targeted attack, e.g., forcing a tracker to follow the ground-truth trajectory with specified offsets, to be video-agnostic and free from inference in a network. |
ZHENBANG LI et. al. | arxiv-cs.CV | 2021-05-06 |
| 19 | Dynamic Defense Approach for Adversarial Robustness in Deep Neural Networks Via Stochastic Ensemble Smoothed Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the dynamic defense approach in cyberspace, this paper builds upon stochastic ensemble smoothing based on defense method of random smoothing and model ensemble. |
Ruoxi Qin; Linyuan Wang; Xingyuan Chen; Xuehui Du; Bin Yan; | arxiv-cs.CR | 2021-05-06 |
| 20 | DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose DeepSMOTE – a novel oversampling algorithm for deep learning models. |
Damien Dablain; Bartosz Krawczyk; Nitesh V. Chawla; | arxiv-cs.CV | 2021-05-05 |
| 21 | Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To align the correct semantic categories across domains, we propose a contrastive learning approach that adapts category-wise centroids across domains. |
Robert A. Marsden; Alexander Bartler; Mario Döbler; Bin Yang; | arxiv-cs.CV | 2021-05-05 |
| 22 | VQCPC-GAN: Variable-length Adversarial Audio Synthesis Using Vector-Quantized Contrastive Predictive Coding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents VQCPC-GAN, an adversarial framework for synthesizing variable-length audio by exploiting Vector-Quantized Contrastive Predictive Coding (VQCPC). |
Javier Nistal; Cyran Aouameur; Stefan Lattner; Gaël Richard; | arxiv-cs.SD | 2021-05-04 |
| 23 | GANs for Urban Design Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The topic investigated in this paper is the application of Generative Adversarial Networks to the design of an urban block. |
Stanislava Fedorova; | arxiv-cs.CV | 2021-05-04 |
| 24 | Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a generative inverse reinforcement learning for user behavioral preference modelling, to address the above issues. |
XIAOCONG CHEN et. al. | arxiv-cs.LG | 2021-05-03 |
| 25 | Synthesizing Time-series Wound Prognosis Factors from Electronic Medical Records Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we developed time series medical generative adversarial networks (GANs) to generate synthetic wound prognosis factors using very limited information collected during routine care in a specialized wound care facility. |
FARNAZ H. FOOMANI et. al. | arxiv-cs.AI | 2021-05-03 |
| 26 | GRNN: Generative Regression Neural Network — A Data Leakage Attack for Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that, in Federated Learning (FL) system, image-based privacy data can be easily recovered in full from the shared gradient only via our proposed Generative Regression Neural Network (GRNN). |
Hanchi Ren; Jingjing Deng; Xianghua Xie; | arxiv-cs.LG | 2021-05-02 |
| 27 | An End-to-End and Accurate PPG-based Respiratory Rate Estimation Approach Using Cycle Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an end-to-end and accurate pipeline for RR estimation using Cycle Generative Adversarial Networks (CycleGAN) to reconstruct respiratory signals from raw PPG signals. |
Seyed Amir Hossein Aqajari; Rui Cao; Amir Hosein Afandizadeh Zargari; Amir M. Rahmani; | arxiv-cs.LG | 2021-05-02 |
| 28 | Multi-Robot Coordination and Planning in Uncertain and Adversarial Environments Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this report, we review recent algorithmic development in making multi-robot systems robust to environmental uncertainties, failures, and adversarial attacks. |
Lifeng Zhou; Pratap Tokekar; | arxiv-cs.RO | 2021-05-02 |
| 29 | Stabilization of Generative Adversarial Networks Via Noisy Scale-space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on these observations, we propose a data representation for GANs, called noisy scale-space, that recursively applies the smoothing with noise to data in order to preserve the data variance while replacing high-frequency information by random data, leading to a coarse-to-fine training of GANs. |
Kensuke Nakamura; Simon Korman; Byung-Woo Hong; | arxiv-cs.LG | 2021-05-01 |
| 30 | Feature Disentanglement in Generating Three-dimensional Structure from Two-dimensional Slice with SliceGAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Among these, a recent deep generative model, dubbed sliceGAN, proposed a new way of using the generative adversarial network (GAN) to capture the micro-structural characteristics of a two-dimensional (2D) slice and generate three-dimensional (3D) volumes with similar properties. |
Hyungjin Chung; Jong Chul Ye; | arxiv-cs.CV | 2021-05-01 |
| 31 | On The Adversarial Robustness of Quantized Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we investigate and model the accuracy of quantized neural networks on adversarially-perturbed images. |
Micah Gorsline; James Smith; Cory Merkel; | arxiv-cs.LG | 2021-05-01 |
| 32 | Semantic Relation Preserving Knowledge Distillation for Image-to-Image Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel method to address this problem by applying knowledge distillation together with distillation of a semantic relation preserving matrix. |
Zeqi Li; Ruowei Jiang; Parham Aarabi; | arxiv-cs.CV | 2021-04-30 |
| 33 | TREND: Truncated Generalized Normal Density Estimation of Inception Embeddings for Accurate GAN Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that this is an over-simplified assumption, which may lead to unreliable evaluation results, and more accurate density estimation can be achieved using a truncated generalized normal distribution. |
Junghyuk Lee; Jong-Seok Lee; | arxiv-cs.CV | 2021-04-30 |
| 34 | StyleMapGAN: Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose StyleMapGAN: the intermediate latent space has spatial dimensions, and a spatially variant modulation replaces AdaIN. |
Hyunsu Kim; Yunjey Choi; Junho Kim; Sungjoo Yoo; Youngjung Uh; | arxiv-cs.CV | 2021-04-30 |
| 35 | Unsupervised Data Augmentation for Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, we propose a framework making use of Generative Adversarial Networks(GAN) to perform unsupervised data augmentation. |
Yichen Zhang; Zeyang Song; Wenbo Li; | arxiv-cs.CV | 2021-04-30 |
| 36 | Data-driven Full-waveform Inversion Surrogate Using Conditional Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose a method of generating velocity field models, as detailed as those obtained through FWI, using a conditional generative adversarial network (cGAN) with multiple inputs. |
Saraiva Marcus; Forechi Avelino; de Oliveira Neto Jorcy; DelRey Antonio; Rauber Thomas; | arxiv-cs.LG | 2021-04-30 |
| 37 | Continuous Face Aging Via Self-estimated Residual Age Embedding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a unified network structure that embeds a linear age estimator into a GAN-based model, where the embedded age estimator is trained jointly with the encoder and decoder to estimate the age of a face image and provide a personalized target age embedding for age progression/regression. |
Zeqi Li; Ruowei Jiang; Parham Aarabi; | arxiv-cs.CV | 2021-04-30 |
| 38 | An Adversarial Transfer Network for Knowledge Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an adversarial embedding transfer network ATransN, which transfers knowledge from one or more teacher knowledge graphs to a target one through an aligned entity set without explicit data leakage. |
Huijuan Wang; Shuangyin Li; Rong Pan; | arxiv-cs.CL | 2021-04-30 |
| 39 | Black-box Adversarial Attacks Using Evolution Strategies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we compare three well-known evolution strategies on the generation of black-box adversarial attacks for image classification tasks. |
Hao Qiu; Leonardo Lucio Custode; Giovanni Iacca; | arxiv-cs.CV | 2021-04-30 |
| 40 | Towards Harmonized Regional Style Transfer and Manipulation for Facial Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the problem of harmonized regional style transfer and manipulation for facial images. |
Cong Wang; Fan Tang; Yong Zhang; Weiming Dong; Tieru Wu; | arxiv-cs.MM | 2021-04-29 |
| 41 | Text2Video: Text-driven Talking-head Video Synthesis with Phonetic Dictionary Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel approach to synthesize video from the text. |
Sibo Zhang; Jiahong Yuan; Miao Liao; Liangjun Zhang; | arxiv-cs.CV | 2021-04-29 |
| 42 | Adversarial Multi-task Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential Equations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To improve the generalizability, we introduce the novel approach of employing multi-task learning techniques, the uncertainty-weighting loss and the gradients surgery, in the context of learning PDE solutions. |
Pongpisit Thanasutives; Ken-ichi Fukui; Masayuki Numao; | arxiv-cs.LG | 2021-04-29 |
| 43 | Analytical Bounds on The Local Lipschitz Constants of ReLU Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we determine analytical upper bounds on the local Lipschitz constants of feedforward neural networks with ReLU activation functions. |
Trevor Avant; Kristi A. Morgansen; | arxiv-cs.LG | 2021-04-29 |
| 44 | Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a semantic consistency and identity mapping multi-component generative adversarial network (SC-IMGAN) which provides style adaptation from one to many domains. |
Amena Khatun; Simon Denman; Sridha Sridharan; Clinton Fookes; | arxiv-cs.CV | 2021-04-28 |
| 45 | Pose-driven Attention-guided Image Generation for Person Re-Identification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this issue, in this paper we propose an end-to-end pose-driven attention-guided generative adversarial network, to generate multiple poses of a person. |
Amena Khatun; Simon Denman; Sridha Sridharan; Clinton Fookes; | arxiv-cs.CV | 2021-04-28 |
| 46 | MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs. |
YAXING WANG et. al. | arxiv-cs.CV | 2021-04-28 |
| 47 | Preserving Semantic Consistency in Unsupervised Domain Adaptation Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an end-to-end novel semantic consistent generative adversarial network (SCGAN). |
Mohammad Mahfujur Rahman; Clinton Fookes; Sridha Sridharan; | arxiv-cs.CV | 2021-04-28 |
| 48 | AdvHaze: Adversarial Haze Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we instead introduce a novel adversarial attack method based on haze, which is a common phenomenon in real-world scenery. |
Ruijun Gao; Qing Guo; Felix Juefei-Xu; Hongkai Yu; Wei Feng; | arxiv-cs.CV | 2021-04-28 |
| 49 | Unsupervised 3D Shape Completion Through GAN Inversion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast to previous fully supervised approaches, in this paper we present ShapeInversion, which introduces Generative Adversarial Network (GAN) inversion to shape completion for the first time. |
JUNZHE ZHANG et. al. | arxiv-cs.CV | 2021-04-27 |
| 50 | End-to-End Video-To-Speech Synthesis Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a new end-to-end video-to-speech model based on Generative Adversarial Networks (GANs) which translates spoken video to waveform end-to-end without using any intermediate representation or separate waveform synthesis algorithm. |
RODRIGO MIRA et. al. | arxiv-cs.LG | 2021-04-27 |
| 51 | Adaptive Adversarial Training for Meta Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we attempt to improve the robustness of MRL. |
Shiqi Chen; Zhengyu Chen; Donglin Wang; | arxiv-cs.LG | 2021-04-27 |
| 52 | SrvfNet: A Generative Network for Unsupervised Multiple Diffeomorphic Shape Alignment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present SrvfNet, a generative deep learning framework for the joint multiple alignment of large collections of functional data comprising square-root velocity functions (SRVF) to their templates. |
Elvis Nunez; Andrew Lizarraga; Shantanu H. Joshi; | arxiv-cs.CV | 2021-04-27 |
| 53 | CAGAN: Text-To-Image Generation with Combined Attention GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose the Combined Attention Generative Adversarial Network (CAGAN) to generate photo-realistic images according to textual descriptions. |
Henning Schulze; Dogucan Yaman; Alexander Waibel; | arxiv-cs.CV | 2021-04-26 |
| 54 | Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a framework for conducting model extraction attacks against image translation models, and show that the adversary can successfully extract functional surrogate models. |
Sebastian Szyller; Vasisht Duddu; Tommi Gröndahl; N. Asokan; | arxiv-cs.LG | 2021-04-26 |
| 55 | 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; | arxiv-cs.CV | 2021-04-26 |
| 56 | Inner-ear Augmented Metal Artifact Reduction with Simulation-based 3D Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the context of post-operative high-resolution {CT} imaging, we propose a 3D metal {artifact} reduction algorithm based on a generative adversarial neural network. |
WANG ZIHAO et. al. | arxiv-cs.CV | 2021-04-26 |
| 57 | VCGAN: Video Colorization with Hybrid Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a hybrid recurrent Video Colorization with Hybrid Generative Adversarial Network (VCGAN), an improved approach to video colorization using end-to-end learning. |
YUZHI ZHAO et. al. | arxiv-cs.CV | 2021-04-26 |
| 58 | Launching Adversarial Attacks Against Network Intrusion Detection Systems for IoT Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our work evaluates both traditional machine learning and deep learning models’ robustness using the Bot-IoT dataset. |
PAVLOS PAPADOPOULOS et. al. | arxiv-cs.LG | 2021-04-26 |
| 59 | Making GAN-Generated Images Difficult To Spot: A New Attack Against Synthetic Image Detectors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new anti-forensic attack capable of fooling GAN-generated image detectors. |
Xinwei Zhao; Matthew C. Stamm; | arxiv-cs.CV | 2021-04-25 |
| 60 | An Adaptive Learning Based Generative Adversarial Network for One-To-One Voice Conversion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an adaptive learning-based GAN model called ALGAN-VC for an efficient one-to-one VC of speakers. |
Sandipan Dhar; Nanda Dulal Jana; Swagatam Das; | arxiv-cs.SD | 2021-04-25 |
| 61 | Supervised Anomaly Detection Via Conditional Generative Adversarial Network and Ensemble Active Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a new supervised anomaly detector through introducing the novel Ensemble Active Learning Generative Adversarial Network (EAL-GAN). |
Zhi Chen; Jiang Duan; Li Kang; Guoping Qiu; | arxiv-cs.LG | 2021-04-24 |
| 62 | Sketch-based Normal Map Generation with Geometric Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a deep generative model for generating normal maps from users sketch with geometric sampling. |
Yi He; Haoran Xie; Chao Zhang; Xi Yang; Kazunori Miyata; | arxiv-cs.CV | 2021-04-23 |
| 63 | Improving Neural Silent Speech Interface Models By Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we evaluate this adversarial training framework in the articulatory-to-acoustic mapping task, where the goal is to reconstruct the speech signal from a recording of the movement of articulatory organs. |
Amin Honarmandi Shandiz; László Tóth; Gábor Gosztolya; Alexandra Markó; Tamás Gábor Csapó; | arxiv-cs.SD | 2021-04-23 |
| 64 | Region-Adaptive Deformable Network for Image Quality Assessment Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose the reference-oriented deformable convolution, which can improve the performance of an IQA network on GAN-based distortion by adaptively considering this misalignment. |
SHUWEI SHI et. al. | arxiv-cs.CV | 2021-04-23 |
| 65 | Safe Fakes: Evaluating Face Anonymizers for Face Detectors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To our knowledge, this paper presents the first empirical study on the effect of image anonymization on supervised training of face detectors. |
Sander R. Klomp; Matthew van Rijn; Rob G. J. Wijnhoven; Cees G. M. Snoek; Peter H. N. de With; | arxiv-cs.CV | 2021-04-23 |
| 66 | Ensembles of GANs for Synthetic Training Data Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work investigates the use of synthetic images, created by generative adversarial networks (GANs), as the only source of training data. |
Gabriel Eilertsen; Apostolia Tsirikoglou; Claes Lundström; Jonas Unger; | arxiv-cs.CV | 2021-04-23 |
| 67 | Towards Adversarial Patch Analysis and Certified Defense Against Crowd Counting Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a robust attack strategy called Adversarial Patch Attack with Momentum (APAM) to systematically evaluate the robustness of crowd counting models, where the attacker’s goal is to create an adversarial perturbation that severely degrades their performances, thus leading to public safety accidents (e.g., stampede accidents). |
QIMING WU et. al. | arxiv-cs.CV | 2021-04-22 |
| 68 | Attribute-Modulated Generative Meta Learning for Zero-Shot Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Existing meta generative approaches pursue a common model shared across task distributions; in contrast, we aim to construct a generative network adaptive to task characteristics. |
Yun Li; Zhe Liu; Lina Yao; Xianzhi Wang; Can Wang; | arxiv-cs.AI | 2021-04-22 |
| 69 | Federated Traffic Synthesizing and Classification Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a novel framework, Federated Generative Adversarial Networks and Automatic Classification (FGAN-AC), which integrates decentralized data synthesizing with traffic classification. |
CHENXIN XU et. al. | arxiv-cs.LG | 2021-04-21 |
| 70 | Causal-TGAN: Generating Tabular Data Using Causal Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a causal model named Causal Tabular Generative Neural Network (Causal-TGAN) to generate synthetic tabular data using the tabular data’s causal information. |
Bingyang Wen; Luis Oliveros Colon; K. P. Subbalakshmi; R. Chandramouli; | arxiv-cs.LG | 2021-04-21 |
| 71 | Mixture of Robust Experts (MoRE): A Flexible Defense Against Multiple Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, through a gating mechanism, we assemble a set of expert networks, each one either adversarially trained to deal with a particular perturbation type or normally trained for boosting accuracy on clean data. |
HAO CHENG et. al. | arxiv-cs.LG | 2021-04-21 |
| 72 | Dual Head Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel technique Dual Head Adversarial Training (DH-AT) to further improve the robustness of existing adversarial training methods. |
Yujing Jiang; Xingjun Ma; Sarah Monazam Erfani; James Bailey; | arxiv-cs.LG | 2021-04-21 |
| 73 | Jacobian Regularization for Mitigating Universal Adversarial Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we derive upper bounds for the effectiveness of UAPs based on norms of data-dependent Jacobians. |
Kenneth T. Co; David Martinez Rego; Emil C. Lupu; | arxiv-cs.LG | 2021-04-21 |
| 74 | Semantic Segmentation By Improved Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, an improved Generative Adversarial Networks (GANs) for image semantic segmentation task (semantic segmentation by GANs, Seg-GAN) is proposed to facilitate further segmentation research. |
ZENGSHUN ZHAOA et. al. | arxiv-cs.CV | 2021-04-20 |
| 75 | Disentangled Face Identity Representations for Joint 3D Face Recognition and Expression Neutralisation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new deep learning-based approach for disentangling face identity representations from expressive 3D faces. |
Anis Kacem; Kseniya Cherenkova; Djamila Aouada; | arxiv-cs.CV | 2021-04-20 |
| 76 | Network Defense Is Not A Game Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Hence, we propose to define network defense tasks as distributions of network environments, to: (i) enable research to apply modern AI techniques, such as unsupervised curriculum learning and reinforcement learning for network defense; and, (ii) facilitate the design of well-defined challenges that can be used to compare approaches for autonomous cyberdefense. |
Andres Molina-Markham; Ransom K. Winder; Ahmad Ridley; | arxiv-cs.CR | 2021-04-20 |
| 77 | Extraction of Hierarchical Functional Connectivity Components in Human Brain Using Adversarial Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The paper aims to use current advancements in adversarial learning to estimate interpretable hierarchical patterns in the human brain using rsfMRI data, which are robust to adversarial effects such as inter-scanner variations. |
Dushyant Sahoo; Christos Davatzikos; | arxiv-cs.LG | 2021-04-20 |
| 78 | Adversarial Training for Deep Learning-based Intrusion Detection Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In security-critical areas, such attacks can cause serious damage; therefore, in this paper, we examine the effect of adversarial attacks on deep learning-based intrusion detection. |
Islam Debicha; Thibault Debatty; Jean-Michel Dricot; Wim Mees; | arxiv-cs.CR | 2021-04-20 |
| 79 | MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a multilayer defense-in-depth framework for AE detection, namely MixDefense. |
Yang Yijun; Gao Ruiyuan; Li Yu; Lai Qiuxia; Xu Qiang; | arxiv-cs.CR | 2021-04-20 |
| 80 | Coarse-to-Fine Searching for Efficient Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper studies the neural architecture search (NAS) problem for developing efficient generator networks. |
Jiahao Wang; Han Shu; Weihao Xia; Yujiu Yang; Yunhe Wang; | arxiv-cs.CV | 2021-04-19 |
| 81 | Surrogate Gradient Field for Latent Space Manipulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the first method that enables manipulation with multidimensional condition such as keypoints and captions. |
Minjun Li; Yanghua Jin; Huachun Zhu; | arxiv-cs.CV | 2021-04-19 |
| 82 | Axial-to-lateral Super-resolution for 3D Fluorescence Microscopy Using Unsupervised Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, here we present a deep-learning-enabled unsupervised super-resolution technique that enhances anisotropic images in volumetric fluorescence microscopy. |
HYOUNGJUN PARK et. al. | arxiv-cs.CV | 2021-04-19 |
| 83 | Quaternion Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, here we propose a family of quaternion-valued generative adversarial networks (QGANs). |
Eleonora Grassucci; Edoardo Cicero; Danilo Comminiello; | arxiv-cs.LG | 2021-04-19 |
| 84 | Calibration and Consistency of Adversarial Surrogate Losses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an extensive study of this question, including a detailed analysis of the H-calibration and H-consistency of adversarial surrogate losses. |
Pranjal Awasthi; Natalie Frank; Anqi Mao; Mehryar Mohri; Yutao Zhong; | arxiv-cs.LG | 2021-04-19 |
| 85 | LAFEAT: Piercing Through Adversarial Defenses with Latent Features Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that latent features in certain robust models are surprisingly susceptible to adversarial attacks. |
Yunrui Yu; Xitong Gao; Cheng-Zhong Xu; | arxiv-cs.LG | 2021-04-19 |
| 86 | 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. | arxiv-cs.LG | 2021-04-19 |
| 87 | Direction-Aggregated Attack for Transferable Adversarial Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the Direction-Aggregated adversarial attacks that deliver transferable adversarial examples. |
Tianjin Huang; Vlado Menkovski; Yulong Pei; YuHao Wang; Mykola Pechenizkiy; | arxiv-cs.LG | 2021-04-19 |
| 88 | Adversarial Diffusion Attacks on Graph-based Traffic Prediction Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To conduct the diffusion attack, we propose a novel attack algorithm, which consists of two major components: 1) approximating the gradient of the black-box prediction model with Simultaneous Perturbation Stochastic Approximation (SPSA); 2) adapting the knapsack greedy algorithm to select the attack nodes. |
Lyuyi Zhu; Kairui Feng; Ziyuan Pu; Wei Ma; | arxiv-cs.LG | 2021-04-19 |
| 89 | Improving Adversarial Robustness Using Proxy Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we improve robust accuracy by up to 6.1% and 5.7% in $l_{\infty}$ and $l_2$ threat model, and certified robust accuracy by 6.7% over baselines not using proxy distributions on the CIFAR-10 dataset. |
VIKASH SEHWAG et. al. | arxiv-cs.LG | 2021-04-19 |
| 90 | An Uncertainty-aware Hierarchical Probabilistic Network for Early Prediction, Quantification and Segmentation of Pulmonary Tumour Growth Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we present a novel method based on a deep hierarchical generative and probabilistic framework that, according to radiological guidelines, predicts tumour growth, quantifies its size and provides a semantic appearance of the future nodule. |
XAVIER RAFAEL-PALOU et. al. | arxiv-cs.CV | 2021-04-18 |
| 91 | Generative Context Pair Selection for Multi-hop Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a generative context selection model for multi-hop question answering that reasons about how the given question could have been generated given a context pair. |
DHEERU DUA et. al. | arxiv-cs.CL | 2021-04-18 |
| 92 | Fashion-Guided Adversarial Attack on Person Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the first adversarial example based method for attacking human instance segmentation networks, namely person segmentation networks in short, which are harder to fool than classification networks. |
Marc Treu; Trung-Nghia Le; Huy H. Nguyen; Junichi Yamagishi; Isao Echizen; | arxiv-cs.CV | 2021-04-16 |
| 93 | Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show that a combination of robust fixed-point quantization, weight clipping, as well as random bit error training (RandBET) or adversarial bit error training (AdvBET) improves robustness against random or adversarial bit errors in quantized DNN weights significantly. |
David Stutz; Nandhini Chandramoorthy; Matthias Hein; Bernt Schiele; | arxiv-cs.LG | 2021-04-16 |
| 94 | Uncertainty Surrogates for Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we introduce a novel way of estimating prediction uncertainty in deep networks through the use of uncertainty surrogates. |
Radhakrishna Achanta; Natasa Tagasovska; | arxiv-cs.LG | 2021-04-16 |
| 95 | Learning Evolved Combinatorial Symbols with A Neuro-symbolic Generative Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a neuro-symbolic generative model which combines the strengths of previous approaches to concept learning. |
Matthias Hofer; Tuan Anh Le; Roger Levy; Josh Tenenbaum; | arxiv-cs.CL | 2021-04-16 |
| 96 | A Novel Approach to Curiosity and Explainable Reinforcement Learning Via Interpretable Sub-Goals Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe a curious subgoal focused agent to address both these challenges. |
Connor van Rossum; Candice Feinberg; Adam Abu Shumays; Kyle Baxter; Benedek Bartha; | arxiv-cs.LG | 2021-04-14 |
| 97 | Stochastic-Adversarial Channels : Online Adversaries With Feedback Snooping Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider stochastic-adversarial mixed noise models. |
Vinayak Suresh; Eric Ruzomberka; David J. Love; | arxiv-cs.IT | 2021-04-14 |
| 98 | Orthogonalizing Convolutional Layers with The Cayley Transform Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose and evaluate an alternative approach to directly parameterize convolutional layers that are constrained to be orthogonal. |
Asher Trockman; J. Zico Kolter; | arxiv-cs.LG | 2021-04-14 |
| 99 | Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification Using Axial-GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we introduce the task of thermal-to-visible face verification from low-resolution thermal images. |
Rakhil Immidisetti; Shuowen Hu; Vishal M. Patel; | arxiv-cs.CV | 2021-04-13 |
| 100 | GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, to address the limit of GAIL, we propose GAN-Based Interactive Reinforcement Learning (GAIRL) from demonstration and human evaluative feedback by combining the advantages of GAIL and interactive reinforcement learning. |
JIE HUANG et. al. | arxiv-cs.LG | 2021-04-13 |
| 101 | Machine-learned 3D Building Vectorization from Satellite Imagery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a machine learning based approach for automatic 3D building reconstruction and vectorization. |
Yi Wang; Stefano Zorzi; Ksenia Bittner; | arxiv-cs.CV | 2021-04-13 |
| 102 | Automatic Correction of Internal Units in Generative Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we devise a method that automatically identifies the internal units generating various types of artifact images. |
Ali Tousi; Haedong Jeong; Jiyeon Han; Hwanil Choi; Jaesik Choi; | arxiv-cs.CV | 2021-04-13 |
| 103 | UPB at SemEval-2021 Task 7: Adversarial Multi-Task Learning for Detecting and Rating Humor and Offense Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we describe our adversarial multi-task network, AMTL-Humor, used to detect and rate humor and offensive texts from Task 7 at SemEval-2021. |
Răzvan-Alexandru Smădu; Dumitru-Clementin Cercel; Mihai Dascalu; | arxiv-cs.CL | 2021-04-13 |
| 104 | An Adversarial Imitation Click Model for Information Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework, Adversarial Imitation Click Model (AICM), based on imitation learning. |
XINYI DAI et. al. | arxiv-cs.IR | 2021-04-13 |
| 105 | Mitigating Adversarial Attack for Compute-in-Memory Accelerator Utilizing On-chip Finetune Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Compute-in-memory (CIM) has been proposed to accelerate the convolution neural network (CNN) computation by implementing parallel multiply and accumulation in analog domain. … |
Shanshi Huang; Hongwu Jiang; Shimeng Yu; | arxiv-cs.LG | 2021-04-13 |
| 106 | Adversarial Autoencoders and Adversarial LSTM for Improved Forecasts of Urban Air Pollution Simulations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents an approach to improve the forecast of computational fluid dynamics (CFD) simulations of urban air pollution using deep learning, and most specifically adversarial training. |
César Quilodrán-Casas; Rossella Arcucci; Laetitia Mottet; Yike Guo; Christopher Pain; | arxiv-cs.LG | 2021-04-13 |
| 107 | Diamond in The Rough: Improving Image Realism By Traversing The GAN Latent Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Formally, we present an unsupervised method to find a direction in the latent space that aligns with improved photo-realism. |
Jeffrey Wen; Fabian Benitez-Quiroz; Qianli Feng; Aleix Martinez; | arxiv-cs.CV | 2021-04-12 |
| 108 | Understanding Overparameterization in Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a comprehensive analysis of the importance of model overparameterization in GANs both theoretically and empirically. |
YOGESH BALAJI et. al. | arxiv-cs.LG | 2021-04-12 |
| 109 | Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework for discriminative pixel-level tasks using a generative model of both images and labels. |
Daiqing Li; Junlin Yang; Karsten Kreis; Antonio Torralba; Sanja Fidler; | arxiv-cs.CV | 2021-04-12 |
| 110 | Fruit Quality and Defect Image Classification with Conditional GAN Data Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The goals of this study are to further enable real-world usage by improving generalisation with data augmentation as well as to reduce overfitting and energy usage through model pruning. |
Jordan J. Bird; Chloe M. Barnes; Luis J. Manso; Anikó Ekárt; Diego R. Faria; | arxiv-cs.CV | 2021-04-12 |
| 111 | Dual Discriminator Adversarial Distillation for Data-free Model Compression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this problem, we propose a novel data-free approach in this paper, named Dual Discriminator Adversarial Distillation (DDAD) to distill a neural network without any training data or meta-data. |
Haoran Zhao; Xin Sun; Junyu Dong; Hui Yu; Huiyu Zhou; | arxiv-cs.CV | 2021-04-12 |
| 112 | Sparse Coding Frontend for Robust Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a radically different defense trained only on clean images: a sparse coding based frontend which significantly attenuates adversarial attacks before they reach the classifier. |
Can Bakiskan; Metehan Cekic; Ahmet Dundar Sezer; Upamanyu Madhow; | arxiv-cs.LG | 2021-04-12 |
| 113 | Domain Adaptive Monocular Depth Estimation With Semantic Information Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an adversarial training model that leverages semantic information to narrow the domain gap. |
Fei Lu; Hyeonwoo Yu; Jean Oh; | arxiv-cs.CV | 2021-04-12 |
| 114 | UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel unpaired image-to-image translation method that uses denoising diffusion probabilistic models without requiring adversarial training. |
Hiroshi Sasaki; Chris G. Willcocks; Toby P. Breckon; | arxiv-cs.CV | 2021-04-12 |
| 115 | Deep Learning for IoT Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To help IoT data analysis more efficient, we propose a retrieval method based on deep learning (recurrent neural network). |
Tao Lin; | arxiv-cs.LG | 2021-04-12 |
| 116 | SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide a new idea of using generative adversarial network (GAN) for defect segmentation. Moreover, we release a new solar cell EL image dataset named as EL-2019, which includes three types of images: crack, finger interruption and defect-free. |
Binyi Su; Zhong Zhou; Haiyong Chen; Xiaochun Cao; | arxiv-cs.CV | 2021-04-11 |
| 117 | The Many Faces of 1-Lipschitz Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The goal of the paper is to demonstrate that, despite being empirically harder to train, 1-Lipschitz neural networks are theoretically better grounded than unconstrained ones when it comes to classification. |
Louis Béthune; Alberto González-Sanz; Franck Mamalet; Mathieu Serrurier; | arxiv-cs.LG | 2021-04-11 |
| 118 | Physically-Consistent Generative Adversarial Networks for Coastal Flood Visualization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the first deep learning pipeline to ensure physical-consistency in synthetic visual satellite imagery. |
BJÖRN LÜTJENS et. al. | arxiv-cs.CV | 2021-04-10 |
| 119 | MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We analyze the most computationally hard parts of StyleGAN2, and propose changes in the generator network to make it possible to deploy style-based generative networks in the edge devices. |
Sergei Belousov; | arxiv-cs.CV | 2021-04-10 |
| 120 | Unified Source-Filter GAN: Unified Source-filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a unified approach to data-driven source-filter modeling using a single neural network for developing a neural vocoder capable of generating high-quality synthetic speech waveforms while retaining flexibility of the source-filter model to control their voice characteristics. |
Reo Yoneyama; Yi-Chiao Wu; Tomoki Toda; | arxiv-cs.SD | 2021-04-09 |
| 121 | Multimodal Face Synthesis from Visual Attributes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel generative adversarial network that simultaneously synthesizes identity preserving multimodal face images (i.e. visible, sketch, thermal, etc.) from visual attributes without requiring paired data in different domains for training the network. |
Xing Di; Vishal M. Patel; | arxiv-cs.CV | 2021-04-09 |
| 122 | An Empirical Study of The Effects of Sample-Mixing Methods for Efficient Training of Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigated the effect of sample mixing methods, that is, Mixup, CutMix, and newly proposed Smoothed Regional Mix (SRMix), to alleviate this problem. |
Makoto Takamoto; Yusuke Morishita; | arxiv-cs.CV | 2021-04-08 |
| 123 | EGAN: Unsupervised Approach to Class Imbalance Using Transfer Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study we explore an unsupervised approach to address these imbalances by leveraging transfer learning from pre-trained image classification models to encoder-based Generative Adversarial Network (eGAN). |
Ademola Okerinde; Lior Shamir; William Hsu; Tom Theis; Nasik Nafi; | arxiv-cs.LG | 2021-04-08 |
| 124 | Re-designing Cities with Conditional Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a conditional generative adversarial network to redesign a street-level image of urban scenes by generating 1) an urban intervention policy, 2) an attention map that localises where intervention is needed, 3) a high-resolution street-level image (1024 X 1024 or 1536 X1536) after implementing the intervention. We also introduce a new dataset that comprises aligned street-level images of before and after urban interventions from real-life scenarios that make this research possible. |
Mohamed R. Ibrahim; James Haworth; Nicola Christie; | arxiv-cs.CV | 2021-04-08 |
| 125 | Generative Landmarks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a general purpose approach to detect landmarks with improved temporal consistency, and personalization. |
David Ferman; Gaurav Bharaj; | arxiv-cs.CV | 2021-04-08 |
| 126 | PATHATTACK: Attacking Shortest Paths in Complex Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce the Force Path Cut problem, in which there is a specific route the adversary wants to promote by removing a minimum number of edges in the graph. |
BENJAMIN A. MILLER et. al. | arxiv-cs.SI | 2021-04-08 |
| 127 | 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. |
Sébastien Bubeck; Yeshwanth Cherapanamjeri; Gauthier Gidel; Rémi Tachet des Combes; | arxiv-cs.LG | 2021-04-08 |
| 128 | OGGN: A Novel Generalized Oracle Guided Generative Architecture for Modelling Inverse Function of Artificial Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel Generative Neural Network Architecture for modelling the inverse function of an Artificial Neural Network (ANN) either completely or partially. |
Mohammad Aaftab V; Mansi Sharma; | arxiv-cs.LG | 2021-04-08 |
| 129 | FACESEC: A Fine-grained Robustness Evaluation Framework for Face Recognition Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present FACESEC, a framework for fine-grained robustness evaluation of face recognition systems. |
LIANG TONG et. al. | arxiv-cs.CV | 2021-04-08 |
| 130 | Generating Multi-type Sequences of Temporal Events to Improve Fraud Detection in Game Advertising Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we propose using a variant of Time-LSTM cells in combination with a modified version of Sequence Generative Adversarial Generative (SeqGAN)to generate artificial sequences to mimic the fraudulent user patterns in ad traffic. |
Lun Jiang; Nima Salehi Sadghiani; Zhuo Tao; | arxiv-cs.LG | 2021-04-07 |
| 131 | Regularizing Generative Adversarial Networks Under Limited Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes a regularization approach for training robust GAN models on limited data. |
Hung-Yu Tseng; Lu Jiang; Ce Liu; Ming-Hsuan Yang; Weilong Yang; | arxiv-cs.LG | 2021-04-07 |
| 132 | Distilling and Transferring Knowledge Via CGAN-generated Samples for Image Classification and Regression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve the above problems in an all-in-one manner, we propose in this paper a unified KD framework based on conditional generative adversarial networks (cGANs), termed cGAN-KD. |
Xin Ding; Yongwei Wang; Zuheng Xu; Z. Jane Wang; William J. Welch; | arxiv-cs.CV | 2021-04-07 |
| 133 | Universal Adversarial Training with Class-Wise Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we find that a UAP does not attack all classes equally. |
Philipp Benz; Chaoning Zhang; Adil Karjauv; In So Kweon; | arxiv-cs.LG | 2021-04-07 |
| 134 | Improving Robustness of Deep Reinforcement Learning Agents: Environment Attacks Based on Critic Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Alternatively, we propose in this paper to build on gradient-based adversarial attacks, usually used for classification tasks for instance, that we apply on the critic network of the protagonist to identify efficient disturbances of the environment. |
Lucas Schott; Manon Césaire; Hatem Hajri; Sylvain Lamprier; | arxiv-cs.LG | 2021-04-07 |
| 135 | Generalization of GANs Under Lipschitz Continuity and Data Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we make a comprehensive analysis about generalization of GANs. |
Khoat Than; Nghia Vu; | arxiv-cs.LG | 2021-04-06 |
| 136 | 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 a single RGB image in order to boost the recognition accuracy of face recognition (FR) systems. |
Hardik Uppal; Alireza Sepas-Moghaddam; Michael Greenspan; Ali Etemad; | arxiv-cs.CV | 2021-04-06 |
| 137 | OodGAN: Generative Adversarial Network for Out-of-Domain Data Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose OodGAN, a sequential generative adversarial network (SeqGAN) based model for OOD data generation. |
Petr Marek; Vishal Ishwar Naik; Vincent Auvray; Anuj Goyal; | arxiv-cs.CL | 2021-04-06 |
| 138 | ReStyle: A Residual-Based StyleGAN Encoder Via Iterative Refinement 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; | arxiv-cs.CV | 2021-04-06 |
| 139 | Leverage Score Sampling for Complete Mode Coverage in Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a sampling procedure based on ridge leverage scores which significantly improves mode coverage when compared to standard methods and can easily be combined with any GAN. |
Joachim Schreurs; Hannes De Meulemeester; Michaël Fanuel; Bart De Moor; Johan A. K. Suykens; | arxiv-cs.LG | 2021-04-06 |
| 140 | Adversarial Robustness Under Long-Tailed Distribution Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by these observations, we propose a clean yet effective framework, RoBal, which consists of two dedicated modules, a scale-invariant classifier and data re-balancing via both margin engineering at training stage and boundary adjustment during inference. |
Tong Wu; Ziwei Liu; Qingqiu Huang; Yu Wang; Dahua Lin; | arxiv-cs.CV | 2021-04-06 |
| 141 | Automated Performance Testing Based on Active Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an automated test generation method called ACTA for black-box performance testing. |
Ali Sedaghatbaf; Mahshid Helali Moghadam; Mehrdad Saadatmand; | arxiv-cs.SE | 2021-04-05 |
| 142 | Content-Aware GAN Compression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose novel approaches for unconditional GAN compression. |
YUCHEN LIU et. al. | arxiv-cs.CV | 2021-04-05 |
| 143 | Can Audio-visual Integration Strengthen Robustness Under Multimodal Attacks? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to make a systematic study on machines multisensory perception under attacks. |
Yapeng Tian; Chenliang Xu; | arxiv-cs.CV | 2021-04-05 |
| 144 | Distill and Fine-tune: Effective Adaptation from A Black-box Source Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this new problem, we propose a novel two-step adaptation framework called Distill and Fine-tune (Dis-tune). |
Jian Liang; Dapeng Hu; Ran He; Jiashi Feng; | arxiv-cs.CV | 2021-04-04 |
| 145 | Information-theoretic Regularization for Multi-source Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we adopt an information-theoretic approach to identify and resolve the potential adverse effect of the multiple domain discriminators on MDA: disintegration of domain-discriminative information, limited computational scalability, and a large variance in the gradient of the loss during training. |
Geon Yeong Park; Sang Wan Lee; | arxiv-cs.LG | 2021-04-04 |
| 146 | Monte Carlo Simulation of SDEs Using GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a scheme that approximates the path-wise conditional distribution of SDEs for large time steps. |
Jorino van Rhijn; Cornelis W. Oosterlee; Lech A. Grzelak; Shuaiqiang Liu; | arxiv-cs.LG | 2021-04-03 |
| 147 | No Need for Interactions: Robust Model-Based Imitation Learning Using Neural ODE Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate this problem, we come up with a Robust Model-Based Imitation Learning (RMBIL) framework that casts imitation learning as an end-to-end differentiable nonlinear closed-loop tracking problem. |
HaoChih Lin; Baopu Li; Xin Zhou; Jiankun Wang; Max Q. -H. Meng; | arxiv-cs.RO | 2021-04-03 |
| 148 | Deepfake Detection Scheme Based on Vision Transformer and Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Vision Transformer model with distillation methodology for detecting fake videos. |
Young-Jin Heo; Young-Ju Choi; Young-Woon Lee; Byung-Gyu Kim; | arxiv-cs.CV | 2021-04-03 |
| 149 | Mitigating Gradient-based Adversarial Attacks Via Denoising and Compression Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose strategies to combine the advantages of these two defense mechanisms. |
Rehana Mahfuz; Rajeev Sahay; Aly El Gamal; | arxiv-cs.CR | 2021-04-03 |
| 150 | Property-driven Training: All You (N)Ever Wanted to Know About Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In response, various methods such as adversarial training, data-augmentation and Lipschitz robustness training have been proposed as means of improving their robustness. |
MARCO CASADIO et. al. | arxiv-cs.LG | 2021-04-03 |
| 151 | PATE-AAE: Incorporating Adversarial Autoencoder Into Private Aggregation of Teacher Ensembles for Spoken Command Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose using an adversarial autoencoder (AAE) to replace generative adversarial network (GAN) in the private aggregation of teacher ensembles (PATE), a solution for ensuring differential privacy in speech applications. |
Chao-Han Huck Yang; Sabato Marco Siniscalchi; Chin-Hui Lee; | arxiv-cs.SD | 2021-04-02 |
| 152 | An Attention-based Unsupervised Adversarial Model for Movie Review Spam Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper focuses primarily on a neglected emerging domain – movie review, and develops a novel unsupervised spam detection model with an attention mechanism. |
Yuan Gao; Maoguo Gong; Yu Xie; A. K. Qin; | arxiv-cs.MM | 2021-04-02 |
| 153 | Data Augmentation with Manifold Barycenters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new way of representing the available knowledge in the manifold of data barycenters. |
Iaroslav Bespalov; Nazar Buzun; Oleg Kachan; Dmitry V. Dylov; | arxiv-cs.CV | 2021-04-02 |
| 154 | In&Out : Diverse Image Outpainting Via GAN Inversion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we formulate the problem from the perspective of inverting generative adversarial networks. |
YEN-CHI CHENG et. al. | arxiv-cs.CV | 2021-04-01 |
| 155 | Drug Discovery Approaches Using Quantum Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a suite of quantum machine learning techniques e.g., generative adversarial network (GAN), convolutional neural network (CNN) and variational auto-encoder (VAE) to generate small drug molecules, classify binding pockets in proteins, and generate large drug molecules, respectively. |
JUNDE LI et. al. | arxiv-cs.ET | 2021-04-01 |
| 156 | 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 for discovering semantic directions in the latent space of pretrained GANs in a self-supervised manner. |
Oğuz Kaan Yüksel; Enis Simsar; Ezgi Gülperi Er; Pinar Yanardag; | arxiv-cs.LG | 2021-04-01 |
| 157 | Partition-Guided GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we break down the challenging task of learning complex high dimensional distributions, supporting diverse data samples, to simpler sub-tasks. |
Mohammadreza Armandpour; Ali Sadeghian; Chunyuan Li; Mingyuan Zhou; | arxiv-cs.LG | 2021-04-01 |
| 158 | Linear Semantics in Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to better understand the semantic representation of GANs, and thereby enable semantic control in GAN’s generation process. |
Jianjin Xu; Changxi Zheng; | arxiv-cs.CV | 2021-04-01 |
| 159 | Exploiting Relationship for Complex-scene Image Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: With the help of relationships, we propose three major updates in the generation framework. |
TIANYU HUA et. al. | arxiv-cs.CV | 2021-04-01 |
| 160 | Improved Image Generation Via Sparse Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to provide a better understanding and design of the image generation process. |
Roy Ganz; Michael Elad; | arxiv-cs.CV | 2021-04-01 |
| 161 | Text to Image Generation with Semantic-Spatial Aware GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A text to image generation (T2I) model aims to generate photo-realistic images which are semantically consistent with the text descriptions. |
Kai Hu; Wentong Liao; Michael Ying Yang; Bodo Rosenhahn; | arxiv-cs.CV | 2021-04-01 |
| 162 | Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification Using Multi-temporal Sentinel-2 Satellite Imagery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate adversarial training of deep neural networks to bridge the domain discrepancy between distinct geographical zones. |
Martini Mauro; Vittorio Mazzia; Aleem Khaliq; Marcello Chiaberge; | arxiv-cs.CV | 2021-04-01 |
| 163 | Domain Invariant Adversarial Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to achieve better trade-off between robust and natural performances by enforcing a domain invariant feature representation. |
Matan Levi; Idan Attias; Aryeh Kontorovich; | arxiv-cs.LG | 2021-04-01 |
| 164 | Bayesian Graph Convolutional Network for Traffic Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Bayesian Graph Convolutional Network (BGCN) framework to alleviate these issues. |
Jun Fu; Wei Zhou; Zhibo Chen; | arxiv-cs.LG | 2021-04-01 |
| 165 | ReMix: Towards Image-to-Image Translation with Limited Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a data augmentation method (ReMix) to tackle this issue. |
Jie Cao; Luanxuan Hou; Ming-Hsuan Yang; Ran He; Zhenan Sun; | arxiv-cs.CV | 2021-03-31 |
| 166 | Attention Map-guided Two-stage Anomaly Detection Using Hard Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this problem, this paper proposes a novel two-stage network consisting of an attention network and an anomaly detection GAN (ADGAN). |
Jou Won Song; Kyeongbo Kong; Ye In Park; Suk-Ju Kang; | arxiv-cs.CV | 2021-03-31 |
| 167 | Generating Multi-scale Maps from Remote Sensing Images Via Series Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: By extending their method, multi-scale RSIs can be trivially translated to multi-scale maps (multi-scale rs2map translation) through scale-wise rs2map models trained for certain scales (parallel strategy). |
Xu Chen; Bangguo Yin; Songqiang Chen; Haifeng Li; Tian Xu; | arxiv-cs.CV | 2021-03-31 |
| 168 | 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. In particular, we propose a new dataset, CityCount, which is derived from the Cityscapes street scenes dataset, to evaluate our approach in a challenging and practically relevant scenario. |
Amrutha Saseendran; Kathrin Skubch; Margret Keuper; | arxiv-cs.CV | 2021-03-31 |
| 169 | Dual Contrastive Loss and Attention for GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose various improvements to further push the boundaries in image generation. |
NING YU et. al. | arxiv-cs.CV | 2021-03-30 |
| 170 | Time-domain Speech Enhancement with Generative Adversarial Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a new framework called Time-domain Speech Enhancement Generative Adversarial Network (TSEGAN), which is an extension of the generative adversarial network (GAN) in time-domain with metric evaluation to mitigate the scaling problem, and provide model training stability, thus achieving performance improvement. |
Feiyang Xiao; Jian Guan; Qiuqiang Kong; Wenwu Wang; | arxiv-cs.SD | 2021-03-30 |
| 171 | What Causes Optical Flow Networks to Be Vulnerable to Physical Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we analyze the cause of the problem and show that the lack of robustness is rooted in the classical aperture problem of optical flow estimation in combination with bad choices in the details of the network architecture. |
Simon Schrodi; Tonmoy Saikia; Thomas Brox; | arxiv-cs.CV | 2021-03-30 |
| 172 | Enabling Data Diversity: Efficient Automatic Augmentation Via Regularized Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To automate medical data augmentation, we propose a regularized adversarial training framework via two min-max objectives and three differentiable augmentation models covering affine transformation, deformation, and appearance changes. |
Yunhe Gao; Zhiqiang Tang; Mu Zhou; Dimitris Metaxas; | arxiv-cs.CV | 2021-03-30 |
| 173 | PointBA: Towards Backdoor Attacks in 3D Point Cloud Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the backdoor attacks in 3D with a unified framework that exploits the unique properties of 3D data and networks. |
XINKE LI et. al. | arxiv-cs.LG | 2021-03-30 |
| 174 | LatentKeypointGAN: Controlling GANs Via Latent Keypoints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce LatentKeypointGAN, a two-stage GAN that is trained end-to-end on the classical GAN objective yet internally conditioned on a set of sparse keypoints with associated appearance embeddings that respectively control the position and style of the generated objects and their parts. |
Xingzhe He; Bastian Wandt; Helge Rhodin; | arxiv-cs.CV | 2021-03-29 |
| 175 | Competing Adaptive Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider in this work a team setting, where a subset of the agents form a team with a common goal while competing with the remainder of the network. |
Stefan Vlaski; Ali H. Sayed; | arxiv-cs.MA | 2021-03-29 |
| 176 | GNeRF: GAN-based Neural Radiance Field Without Posed Camera Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce GNeRF, a framework to marry Generative Adversarial Networks (GAN) with Neural Radiance Field reconstruction for the complex scenarios with unknown and even randomly initialized camera poses. |
QUAN MENG et. al. | arxiv-cs.CV | 2021-03-29 |
| 177 | An Adversarial Human Pose Estimation Network Injected with Graph Structure Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we design a novel generative adversarial network (GAN) to improve the localization accuracy of visible joints when some joints are invisible. |
Lei Tian; Guoqiang Liang; Peng Wang; Chunhua Shen; | arxiv-cs.CV | 2021-03-29 |
| 178 | Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recently, generative adversarial networks (GANs) based methods have significantly improved the quality of image synthesis, but they have not explicitly considered the purpose of recognition. |
Yuke Fang; Jiani Hu; Weihong Deng; | arxiv-cs.CV | 2021-03-29 |
| 179 | PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with A Pose Estimator and An Auxiliary Classifier Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Although Generative Adversarial Networks (GANs) are successfully applied to diverse fields, training GANs on synthetic aperture radar (SAR) data is a challenging task mostly due … |
Jihyong Oh; Munchurl Kim; | arxiv-cs.CV | 2021-03-29 |
| 180 | Deep Image Compositing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to cater to this problem by making composite images look realistic. So we created the dataset and will also make the dataset publicly available for benchmarking. |
Shivangi Aneja; Soham Mazumder; | arxiv-cs.CV | 2021-03-29 |
| 181 | Fooling LiDAR Perception Via Adversarial Trajectory Perturbation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We demonstrate such possibilities for the first time: instead of directly attacking point cloud coordinates which requires tampering with the raw LiDAR readings, only adversarial spoofing of a self-driving car’s trajectory with small perturbations is enough to make safety-critical objects undetectable or detected with incorrect positions. |
Yiming Li; Congcong Wen; Felix Juefei-Xu; Chen Feng; | arxiv-cs.CV | 2021-03-29 |
| 182 | Enhancing The Transferability of Adversarial Attacks Through Variance Tuning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a new method called variance tuning to enhance the class of iterative gradient based attack methods and improve their attack transferability. |
Xiaosen Wang; Kun He; | arxiv-cs.AI | 2021-03-29 |
| 183 | ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we support the idea that small input gradients play a key role in this phenomenon, and hence propose to zero the input gradient elements that are small for crafting FGSM attacks. |
Zeinab Golgooni; Mehrdad Saberi; Masih Eskandar; Mohammad Hossein Rohban; | arxiv-cs.LG | 2021-03-29 |
| 184 | Product Semantics Translation from Brain Activity Via Adversarial Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To modify a design semantic of a given product from personalised brain activity via adversarial learning, in this work, we propose a deep generative transformation model to modify product semantics from the brain signal. |
PAN WANG et. al. | arxiv-cs.MM | 2021-03-29 |
| 185 | On The Adversarial Robustness of Visual Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Tested on various white-box and transfer attack settings, we find that ViTs possess better adversarial robustness when compared with convolutional neural networks (CNNs). |
Rulin Shao; Zhouxing Shi; Jinfeng Yi; Pin-Yu Chen; Cho-Jui Hsieh; | arxiv-cs.CV | 2021-03-29 |
| 186 | Automating Defense Against Adversarial Attacks: Discovery of Vulnerabilities and Application of Multi-INT Imagery to Protect Deployed Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work proposes an automated approach to defend these models. |
Josh Kalin; David Noever; Matthew Ciolino; Dominick Hambrick; Gerry Dozier; | arxiv-cs.CR | 2021-03-29 |
| 187 | TULVCAN: Terahertz Ultra-broadband Learning Vehicular Channel-Aware Networking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces novel THz channel-aware spectrum learning solutions that fully disclose the uniqueness of THz channels when performing such ultra-broadband sensing in vehicular environments. |
Chia-Hung Lin; Shih-Chun Lin; Erik Blasch; | arxiv-cs.NI | 2021-03-28 |
| 188 | IUP: An Intelligent Utility Prediction Scheme for Solid-State Fermentation in 5G IoT Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an Intelligent Utility Prediction (IUP) scheme for SSF in 5G Industrial Internet of Things (IoT), including parameter collection and utility prediction of SSF process. |
MIN WANG et. al. | arxiv-cs.LG | 2021-03-28 |
| 189 | Zero-shot Adversarial Quantization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the above issues, we propose a zero-shot adversarial quantization (ZAQ) framework, facilitating effective discrepancy estimation and knowledge transfer from a full-precision model to its quantized model. |
Yuang Liu; Wei Zhang; Jun Wang; | arxiv-cs.CV | 2021-03-28 |
| 190 | Improved Autoregressive Modeling with Distribution Smoothing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by a successful adversarial defense method, we incorporate randomized smoothing into autoregressive generative modeling. |
Chenlin Meng; Jiaming Song; Yang Song; Shengjia Zhao; Stefano Ermon; | arxiv-cs.LG | 2021-03-28 |
| 191 | Continuous Conditional Generative Adversarial Networks (cGAN) with Generator Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To partially alleviate this difficulty, we propose a simple generator regularization term on the GAN generator loss in the form of Lipschitz penalty. |
Yufeng Zheng; Yunkai Zhang; Zeyu Zheng; | arxiv-cs.LG | 2021-03-27 |
| 192 | LiBRe: A Practical Bayesian Approach to Adversarial Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a more practical approach, Lightweight Bayesian Refinement (LiBRe), in the spirit of leveraging Bayesian neural networks (BNNs) for adversarial detection. |
Zhijie Deng; Xiao Yang; Shizhen Xu; Hang Su; Jun Zhu; | arxiv-cs.LG | 2021-03-27 |
| 193 | IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a decision-based black-box attack method for visual object tracking. |
Shuai Jia; Yibing Song; Chao Ma; Xiaokang Yang; | arxiv-cs.CV | 2021-03-27 |
| 194 | OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, to optimize input masking, we have designed a framework consisting of two competing networks, a Mask Module and a Reconstructor. |
John Taylor Jewell; Vahid Reza Khazaie; Yalda Mohsenzadeh; | arxiv-cs.CV | 2021-03-27 |
| 195 | Cyclic Defense GAN Against Speech Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a new defense approach for counteracting with state-of-the-art white and black-box adversarial attack algorithms. |
Mohammad Esmaeilpour; Patrick Cardinal; Alessandro Lameiras Koerich; | arxiv-cs.SD | 2021-03-26 |
| 196 | Ensemble-in-One: Learning Ensemble Within Random Gated Networks for Enhanced Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose ensemble-in-one (EIO), a simple but efficient way to train an ensemble within one random gated network (RGN). |
Yi Cai; Xuefei Ning; Huazhong Yang; Yu Wang; | arxiv-cs.LG | 2021-03-26 |
| 197 | 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; | arxiv-cs.CV | 2021-03-26 |
| 198 | Combating Adversaries with Anti-Adversaries Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the fact that these adversaries are constructed by iteratively minimizing the confidence of a network for the true class label, we propose the anti-adversary layer, aimed at countering this effect. |
MOTASEM ALFARRA et. al. | arxiv-cs.LG | 2021-03-26 |
| 199 | ScanGAN360: A Generative Model of Realistic Scanpaths for 360$^{\circ}$ Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present ScanGAN360, a new generative adversarial approach to address this challenging problem. |
Daniel Martin; Ana Serrano; Alexander W. Bergman; Gordon Wetzstein; Belen Masia; | arxiv-cs.CV | 2021-03-25 |
| 200 | Generative-Adversarial-Networks-based Ghost Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel coincidence recognition method combining ghost imaging (GI) and generative adversarial networks (GAN). |
YUCHEN HE et. al. | arxiv-cs.CV | 2021-03-25 |
| 201 | THAT: Two Head Adversarial Training for Improving Robustness at Scale Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Two Head Adversarial Training (THAT), a two-stream adversarial learning network that is designed to handle the large-scale many-class ImageNet dataset. |
Zuxuan Wu; Tom Goldstein; Larry S. Davis; Ser-Nam Lim; | arxiv-cs.CV | 2021-03-25 |
| 202 | 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; | arxiv-cs.CV | 2021-03-25 |
| 203 | Adversarial Imitation Learning with Trajectorial Augmentation and Correction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a novel augmentation method which preserves the success of the augmented trajectories. |
Dafni Antotsiou; Carlo Ciliberto; Tae-Kyun Kim; | arxiv-cs.LG | 2021-03-25 |
| 204 | Deep-RBF Networks for Anomaly Detection in Automotive Cyber-Physical Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we show how the deep-RBF network can be used for detecting anomalies in CPS regression tasks such as continuous steering predictions. |
Matthew Burruss; Shreyas Ramakrishna; Abhishek Dubey; | arxiv-cs.LG | 2021-03-25 |
| 205 | HufuNet: Embedding The Left Piece As Watermark and Keeping The Right Piece for Ownership Verification in Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these problems, we propose a novel DNN watermarking solution, named HufuNet, for protecting the ownership of DNN models. |
PEIZHUO LV et. al. | arxiv-cs.CR | 2021-03-25 |
| 206 | MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel multi-level adversarial network (MLAN) that aims to address inter-domain inconsistency at both global image level and local region level optimally. |
Jiaxing Huang; Dayan Guan; Shijian Lu; Aoran Xiao; | arxiv-cs.CV | 2021-03-24 |
| 207 | Matched Sample Selection with GANs for Mitigating Attribute Confounding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate such attribute confounding during bias analysis, we propose a matching approach that selects a subset of images from the full dataset with balanced attribute distributions across protected attributes. |
Chandan Singh; Guha Balakrishnan; Pietro Perona; | arxiv-cs.CV | 2021-03-24 |
| 208 | Adversarial Feature Stacking for Accurate and Robust Predictions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this problem, we propose an Adversarial Feature Stacking (AFS) model that can jointly take advantage of features with varied levels of robustness and accuracy, thus significantly alleviating the aforementioned trade-off. |
Faqiang Liu; Rong Zhao; Luping Shi; | arxiv-cs.CV | 2021-03-24 |
| 209 | Vulnerability of Appearance-based Gaze Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the vulnerability of appearance-based gaze estimation. |
Mingjie Xu; Haofei Wang; Yunfei Liu; Feng Lu; | arxiv-cs.CV | 2021-03-24 |
| 210 | SETGAN: Scale and Energy Trade-off GANs for Image Applications on Mobile Platforms Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel approach to trade-off image generation accuracy of a GAN for the energy consumed (compute) at run-time called Scale-Energy Tradeoff GAN (SETGAN). |
Nitthilan Kannappan Jayakodi; Janardhan Rao Doppa; Partha Pratim Pande; | arxiv-cs.CV | 2021-03-23 |
| 211 | Generative Minimization Networks: Training GANs Without Competition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to address this problem by optimizing a different objective that circumvents the min-max structure using the notion of duality gap from game theory. |
Paulina Grnarova; Yannic Kilcher; Kfir Y. Levy; Aurelien Lucchi; Thomas Hofmann; | arxiv-cs.LG | 2021-03-23 |
| 212 | Watermark Faker: Towards Forgery of Digital Image Watermarking Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we make the first attempt to develop digital image watermark fakers by using generative adversarial learning. |
Ruowei Wang; Chenguo Lin; Qijun Zhao; Feiyu Zhu; | arxiv-cs.CR | 2021-03-23 |
| 213 | NNrepair: Constraint-based Repair of Neural Network Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present NNrepair, a constraint-based technique for repairing neural network classifiers. |
Muhammad Usman; Divya Gopinath; Youcheng Sun; Yannic Noller; Corina Pasareanu; | arxiv-cs.LG | 2021-03-23 |
| 214 | CLIP: Cheap Lipschitz Training of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we investigate a variational regularization method named CLIP for controlling the Lipschitz constant of a neural network, which can easily be integrated into the training procedure. |
Leon Bungert; René Raab; Tim Roith; Leo Schwinn; Daniel Tenbrinck; | arxiv-cs.LG | 2021-03-23 |
| 215 | SparseGAN: Sparse Generative Adversarial Network for Text Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the principle of sparse coding, we propose a SparseGAN that generates semantic-interpretable, but sparse sentence representations as inputs to the discriminator. |
Liping Yuan; Jiehang Zeng; Xiaoqing Zheng; | arxiv-cs.CL | 2021-03-22 |
| 216 | Context-Aware Layout to Image Generation with Enhanced Object Appearance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A layout to image (L2I) generation model aims to generate a complicated image containing multiple objects (things) against natural background (stuff), conditioned on a given layout. |
SEN HE et. al. | arxiv-cs.CV | 2021-03-22 |
| 217 | Reward-Reinforced Reinforcement Learning for Multi-agent Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we developed a reward-reinforced generative adversarial network to represent the distribution of the value function, replacing the approximation of Bellman updates. |
Changgang Zheng; Shufan Yang; Juan Parra-Ullauri; Antonio Garcia-Dominguez; Nelly Bencomo; | arxiv-cs.MA | 2021-03-22 |
| 218 | Progressive and Aligned Pose Attention Transfer for Person Image Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a new generative adversarial network for pose transfer, i.e., transferring the pose of a given person to a target pose. |
ZHEN ZHU et. al. | arxiv-cs.CV | 2021-03-22 |
| 219 | Evaluating Post-Training Compression in GANs Using Locality-Sensitive Hashing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose two new precision and recall metrics based on locality-sensitive hashing (LSH), which, on top of increasing the outlier robustness, decrease the complexity of assessing an evaluation sample against $n$ reference samples from $O(n)$ to $O(\log(n))$, if using LSH and KNN, and to $O(1)$, if only applying LSH. |
Gonçalo Mordido; Haojin Yang; Christoph Meinel; | arxiv-cs.LG | 2021-03-22 |
| 220 | Spatio-Temporal Sparsification for General Robust Graph Convolution Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this shortage of robust generalization, we propose to defend the adversarial attacks on GNN through applying the Spatio-Temporal sparsification (called ST-Sparse) on the GNN hidden node representation. |
Mingming Lu; Ya Zhang; | arxiv-cs.LG | 2021-03-22 |
| 221 | Adversarial Feature Augmentation and Normalization for Visual Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings, instead of relying on computationally-expensive pixel-level perturbations. |
TIANLONG CHEN et. al. | arxiv-cs.LG | 2021-03-22 |
| 222 | Adversarially Optimized Mixup for Robust Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we bring these ideas together by adversarially probing the space between datapoints, using projected gradient descent (PGD). |
Jason Bunk; Srinjoy Chattopadhyay; B. S. Manjunath; Shivkumar Chandrasekaran; | arxiv-cs.LG | 2021-03-22 |
| 223 | On The Robustness of Monte Carlo Dropout Trained with Noisy Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Due to its superior performance amongst other selected epistemic uncertainty methods under noisy labels, we focus on Monte Carlo Dropout (MCDropout) and investigate why it is robust when trained with noisy labels. |
Purvi Goel; Li Chen; | arxiv-cs.LG | 2021-03-22 |
| 224 | Conditional Generative Adversarial Networks for Speed Control in Trajectory Simulation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present Conditional Speed GAN (CSG), that allows controlled generation of diverse and socially acceptable trajectories, based on user controlled speed. |
Sahib Julka; Vishal Sowrirajan; Joerg Schloetterer; Michael Granitzer; | arxiv-cs.CV | 2021-03-21 |
| 225 | Natural Perturbed Training for General Robustness of Neural Network Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We focus on the robustness of neural networks for classification. |
Sadaf Gulshad; Arnold Smeulders; | arxiv-cs.CV | 2021-03-21 |
| 226 | ExAD: An Ensemble Approach for Explanation-based Adversarial Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose ExAD, a framework to detect adversarial examples using an ensemble of explanation techniques. |
RAJ VARDHAN et. al. | arxiv-cs.LG | 2021-03-21 |
| 227 | Are High-Frequency Components Beneficial for Training of Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on these, we propose two preprocessing methods eliminating high-frequency differences in GANs training: High-Frequency Confusion (HFC) and High-Frequency Filter (HFF). |
Ziqiang Li; Pengfei Xia; Xue Rui; Yanghui Hu; Bin Li; | arxiv-cs.CV | 2021-03-20 |
| 228 | Efficient Subsampling for Generating High-Quality Images from Conditional Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an efficient method called conditional density ratio estimation in feature space with conditional Softplus loss (cDRE-F-cSP). |
Xin Ding; Yongwei Wang; Z. Jane Wang; William J. Welch; | arxiv-cs.CV | 2021-03-20 |
| 229 | High Resolution Face Editing with Masked GAN Latent Code Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a GAN embedding optimization procedure with spatial and semantic constraints. |
Martin Pernuš; Vitomir Štruc; Simon Dobrišek; | arxiv-cs.CV | 2021-03-20 |
| 230 | Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve the above problem, in this work, we propose a novel method called Adversarial and Contrastive Variational Autoencoder (ACVAE) for sequential recommendation. |
ZHE XIE et. al. | arxiv-cs.IR | 2021-03-19 |
| 231 | Robustness Via Cross-Domain Ensembles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a method for making neural network predictions robust to shifts from the training data distribution. |
Teresa Yeo; Oğuzhan Fatih Kar; Amir Zamir; | arxiv-cs.CV | 2021-03-19 |
| 232 | Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a novel yet efficient method named Ano-Graph for learning and modeling the interaction of normal objects. |
Masoud Pourreza; Mohammadreza Salehi; Mohammad Sabokrou; | arxiv-cs.CV | 2021-03-18 |
| 233 | Impressions2Font: Generating Fonts By Specifying Impressions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes Impressions2Font (Imp2Font) that generates font images with specific impressions. |
Seiya Matsuda; Akisato Kimura; Seiichi Uchida; | arxiv-cs.CV | 2021-03-18 |
| 234 | Using Latent Space Regression to Analyze and Leverage Compositionality in GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate regression into the latent space as a probe to understand the compositional properties of GANs. |
Lucy Chai; Jonas Wulff; Phillip Isola; | arxiv-cs.CV | 2021-03-18 |
| 235 | Large Scale Image Completion Via Co-Modulated Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this challenge, we propose a generic new approach that bridges the gap between image-conditional and recent modulated unconditional generative architectures via co-modulation of both conditional and stochastic style representations. |
SHENGYU ZHAO et. al. | arxiv-cs.CV | 2021-03-18 |
| 236 | Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profiles Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a visual framework to investigate neural network models subjected to adversarial examples, revealing how models’ perception of the adversarial data differs from regular data instances and their relationships with class perception. |
Gabriel D. Cantareira; Rodrigo F. Mello; Fernando V. Paulovich; | arxiv-cs.LG | 2021-03-18 |
| 237 | Noise Modulation: Let Your Model Interpret Itself Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on a digital analogy,we propose noise modulation as an efficient and model-agnostic alternative to train a model that interprets itself with input-gradients. |
Haoyang Li; Xinggang Wang; | arxiv-cs.LG | 2021-03-18 |
| 238 | Reading Isn’t Believing: Adversarial Attacks On Multi-Modal Neurons Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Like previous authors, we show by example that the CLIP model tends to read first, look later, a phenomenon we describe as reading isn’t believing. |
David A. Noever; Samantha E. Miller Noever; | arxiv-cs.LG | 2021-03-18 |
| 239 | Training GANs with Stronger Augmentations Via Contrastive Discriminator Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel way to address these questions by incorporating a recent contrastive representation learning scheme into the GAN discriminator, coined ContraD. |
Jongheon Jeong; Jinwoo Shin; | arxiv-cs.LG | 2021-03-17 |
| 240 | Single Underwater Image Restoration By Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We design our method by leveraging from contrastive learning and generative adversarial networks to maximize mutual information between raw and restored images. Additionally, we release a large-scale real underwater image dataset to support both paired and unpaired training modules. |
JUNLIN HAN et. al. | arxiv-cs.CV | 2021-03-17 |
| 241 | Rapid Treatment Planning for Low-dose-rate Prostate Brachytherapy with TP-GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method that aims to reduce this variability by training a model to learn from a large pool of successful retrospective LDR-PB data (961 patients) and create consistent plans that mimic the high-quality manual plans. |
Tajwar Abrar Aleef; Ingrid T. Spadinger; Michael D. Peacock; Septimiu E. Salcudean; S. Sara Mahdavi; | arxiv-cs.CV | 2021-03-17 |
| 242 | Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we experimentally show that FedGAN generates biased data points under non-independent-and-identically-distributed (non-iid) settings. |
Vaikkunth Mugunthan; Vignesh Gokul; Lalana Kagal; Shlomo Dubnov; | arxiv-cs.LG | 2021-03-17 |
| 243 | Map Completion from Partial Observation Using The Global Structure of Multiple Environmental Maps Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel SLAM method, map completion network-based SLAM (MCN-SLAM), based on a probabilistic generative model incorporating deep neural networks for map completion. |
YUKI KATSUMATA et. al. | arxiv-cs.RO | 2021-03-16 |
| 244 | Adversarial Driving: Attacking End-to-End Autonomous Driving Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this research, we devise two white-box targeted attacks against end-to-end autonomous driving systems. |
Han Wu; Wenjie Ruan; | arxiv-cs.CV | 2021-03-16 |
| 245 | Bio-inspired Robustness: A Review Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a set of criteria for proper evaluation and analyze different models according to these criteria. |
Harshitha Machiraju; Oh-Hyeon Choung; Pascal Frossard; Michael. H Herzog; | arxiv-cs.CV | 2021-03-16 |
| 246 | BLOWN: A Blockchain Protocol for Single-Hop Wireless Networks Under Adversarial SINR Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel consensus protocol named Proof-of-Channel (PoC) leveraging the natural properties of wireless communications, and a BLOWN protocol (BLOckchain protocol for Wireless Networks) for wireless networks under an adversarial SINR model. |
MINGHUI XU et. al. | arxiv-cs.CR | 2021-03-15 |
| 247 | Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. |
Bronya Roni Chernyak; Bhiksha Raj; Tamir Hazan; Joseph Keshet; | arxiv-cs.LG | 2021-03-15 |
| 248 | Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel UDA method for multi-modal cardiac image segmentation. |
Sulaiman Vesal; Mingxuan Gu; Ronak Kosti; Andreas Maier; Nishant Ravikumar; | arxiv-cs.CV | 2021-03-15 |
| 249 | HDTest: Differential Fuzz Testing of Brain-Inspired Hyperdimensional Computing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we design, implement, and evaluate HDTest to test HDC model by automatically exposing unexpected or incorrect behaviors under rare inputs. |
Dongning Ma; Jianmin Guo; Yu Jiang; Xun Jiao; | arxiv-cs.NE | 2021-03-15 |
| 250 | Multi-Discriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a defense approach against end-to-end adversarial attacks developed for cutting-edge speech-to-text systems. |
Mohammad Esmaeilpour; Patrick Cardinal; Alessandro Lameiras Koerich; | arxiv-cs.SD | 2021-03-14 |
| 251 | DivCo: Diverse Conditional Image Synthesis Via Contrastive Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel DivCo framework to properly constrain both positive and negative relations between the generated images specified in the latent space. |
Rui Liu; Yixiao Ge; Ching Lam Choi; Xiaogang Wang; Hongsheng Li; | arxiv-cs.CV | 2021-03-14 |
| 252 | Bangla Handwritten Digit Recognition and Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a Semi-Supervised Generative Adversarial Network or SGAN has been applied to generate Bangla handwritten numerals and it successfully generated Bangla digits. |
Md Fahim Sikder; | arxiv-cs.CV | 2021-03-14 |
| 253 | Mean Field Game GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel mean field games (MFGs) based GAN(generative adversarial network) framework. |
Shaojun Ma; Haomin Zhou; Hongyuan Zha; | arxiv-cs.LG | 2021-03-14 |
| 254 | BreakingBED — Breaking Binary and Efficient Deep Neural Networks By Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we thoroughly study the robustness of uncompressed, distilled, pruned and binarized neural networks against white-box and black-box adversarial attacks (FGSM, PGD, C&W, DeepFool, LocalSearch and GenAttack). |
MANOJ ROHIT VEMPARALA et. al. | arxiv-cs.LG | 2021-03-14 |
| 255 | PhotoApp: Photorealistic Appearance Editing of Head Portraits Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an approach for high-quality intuitive editing of the camera viewpoint and scene illumination in a portrait image. |
MALLIKARJUN B R et. al. | arxiv-cs.CV | 2021-03-13 |
| 256 | Unsupervised Image Transformation Learning Via Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study the image transformation problem by learning the underlying transformations from a collection of images using Generative Adversarial Networks (GANs). |
Kaiwen Zha; Yujun Shen; Bolei Zhou; | arxiv-cs.CV | 2021-03-13 |
| 257 | Attack As Defense: Characterizing Adversarial Examples Using Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel characterization to distinguish adversarial examples from benign ones based on the observation that adversarial examples are significantly less robust than benign ones. |
ZHE ZHAO et. al. | arxiv-cs.CR | 2021-03-13 |
| 258 | Generating Unrestricted Adversarial Examples Via Three Parameters Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As most adversarial examples have restricted their perturbations to $L_{p}$-norm, existing defense methods have focused on these types of perturbations and less attention has been paid to unrestricted adversarial examples; which can create more realistic attacks, able to deceive models without affecting human predictions. |
Hanieh Naderi; Leili Goli; Shohreh Kasaei; | arxiv-cs.CV | 2021-03-13 |
| 259 | Learning Defense Transformers for Counterattacking Adversarial Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, motivated by that adversarial examples are more likely to appear near the classification boundary, we study adversarial examples from a new perspective that whether we can defend against adversarial examples by pulling them back to the original clean distribution. |
Jincheng Li; Jiezhang Cao; Yifan Zhang; Jian Chen; Mingkui Tan; | arxiv-cs.LG | 2021-03-12 |
| 260 | Internal Wasserstein Distance for Adversarial Attack and Defense Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we develop a novel attack method by capturing the distribution of patches in original samples. |
JINCHENG LI et. al. | arxiv-cs.LG | 2021-03-12 |
| 261 | Adversarial Graph Disentanglement Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an Adversarial Disentangled Graph Convolutional Network (ADGCN) for disentangled graph representation learning. |
Shuai Zheng; Zhenfeng Zhu; Zhizhe Liu; Shuiwang Ji; Yao Zhao; | arxiv-cs.LG | 2021-03-12 |
| 262 | HumanGAN: A Generative Model of Humans Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address these limitations and present a generative model for images of dressed humans offering control over pose, local body part appearance and garment style. |
Kripasindhu Sarkar; Lingjie Liu; Vladislav Golyanik; Christian Theobalt; | arxiv-cs.CV | 2021-03-11 |
| 263 | DAFAR: Defending Against Adversaries By Feedback-Autoencoder Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose DAFAR, a feedback framework that allows deep learning models to detect/purify adversarial examples in high effectiveness and universality, with low area and time overhead. |
Haowen Liu; Ping Yi; Hsiao-Ying Lin; Jie Shi; Weidong Qiu; | arxiv-cs.CV | 2021-03-11 |
| 264 | Adversarial Laser Beam: Effective Physical-World Attack to DNNs in A Blink Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show by simply using a laser beam that DNNs are easily fooled. |
RANJIE DUAN et. al. | arxiv-cs.LG | 2021-03-11 |
| 265 | Range-GAN: Range-Constrained Generative Adversarial Network for Conditioned Design Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a conditional deep generative model, Range-GAN, to achieve automatic design synthesis subject to range constraints. |
Amin Heyrani Nobari; Wei Chen; Faez Ahmed; | arxiv-cs.LG | 2021-03-10 |
| 266 | Face Images As Jigsaw Puzzles: Compositional Perception of Human Faces for Machines Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a new scheme to enable generative adversarial networks to learn the distribution of face images composed of smaller parts. |
Mahla Abdolahnejad; Peter Xiaoping Liu; | arxiv-cs.CV | 2021-03-10 |
| 267 | TANTRA: Timing-Based Adversarial Network Traffic Reshaping Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present TANTRA, a novel end-to-end Timing-based Adversarial Network Traffic Reshaping Attack that can bypass a variety of NIDSs. |
Yam Sharon; David Berend; Yang Liu; Asaf Shabtai; Yuval Elovici; | arxiv-cs.CR | 2021-03-10 |
| 268 | CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes an automated method, named CreativeGAN, for generating novel designs. |
Amin Heyrani Nobari; Muhammad Fathy Rashad; Faez Ahmed; | arxiv-cs.LG | 2021-03-10 |
| 269 | Adversarial Regression Learning for Bone Age Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an adversarial regression learning network (ARLNet) for bone age estimation. |
Youshan Zhang; Brian D. Davison; | arxiv-cs.CV | 2021-03-10 |
| 270 | ByteSGAN: A Semi-supervised Generative Adversarial Network for Encrypted Traffic Classification of SDN Edge Gateway in Green Communication Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: With that in mind, we proposed a Generative Adversarial Network (GAN)-based Semi-Supervised Learning Encrypted Traffic Classification method called \emph{ByteSGAN} embedded in SDN Edge Gateway to achieve the goal of traffic classification in a fine-grained manner to further improve network resource utilization. |
Pan Wang; Zixuan Wang; Feng Ye; Xuejiao Chen; | arxiv-cs.CR | 2021-03-09 |
| 271 | SMIL: Multimodal Learning with Severely Missing Modality Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Technically, we propose a new method named SMIL that leverages Bayesian meta-learning in uniformly achieving both objectives. |
MENGMENG MA et. al. | arxiv-cs.CV | 2021-03-09 |
| 272 | Analytically Tractable Inference in Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we are demonstrating how TAGI matches or exceeds the performance of backpropagation, for training classic deep neural network architectures. |
Luong-Ha Nguyen; James-A. Goulet; | arxiv-cs.LG | 2021-03-09 |
| 273 | Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a new task is proposed, namely, weather translation, which refers to transferring weather conditions of the image from one category to another. |
Xuelong Li; Kai Kou; Bin Zhao; | arxiv-cs.CV | 2021-03-09 |
| 274 | Selective and Features Based Adversarial Example Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To trade off these factors, we propose a novel unsupervised detection mechanism that uses the selective prediction, processing model layers outputs, and knowledge transfer concepts in a multi-task learning setting. |
Ahmed Aldahdooh; Wassim Hamidouche; Olivier Déforges; | arxiv-cs.CR | 2021-03-09 |
| 275 | Stabilized Medical Image Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an image-based medical adversarial attack method to consistently produce adversarial perturbations on medical images. |
Gege Qi; Lijun Gong; Yibing Song; Kai Ma; Yefeng Zheng; | arxiv-cs.CV | 2021-03-09 |
| 276 | Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider the problem of obstacle avoidance in simple 3D environments where the robot has to solely rely on a single monocular camera. |
Patrick Wenzel; Torsten Schön; Laura Leal-Taixé; Daniel Cremers; | arxiv-cs.LG | 2021-03-08 |
| 277 | Domain-Robust Visual Imitation Learning with Mutual Information Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new algorithm – called Disentangling Generative Adversarial Imitation Learning (DisentanGAIL) – with the purpose of bypassing such constraints. |
Edoardo Cetin; Oya Celiktutan; | arxiv-cs.LG | 2021-03-08 |
| 278 | Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, this compendium covers energy-based models, variational autoencoders, generative adversarial networks, autoregressive models, normalizing flows, in addition to numerous hybrid approaches. |
Sam Bond-Taylor; Adam Leach; Yang Long; Chris G. Willcocks; | arxiv-cs.LG | 2021-03-08 |
| 279 | An Introduction to Deep Generative Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our goal is to enable and motivate the reader to contribute to this proliferating research area. |
Lars Ruthotto; Eldad Haber; | arxiv-cs.LG | 2021-03-08 |
| 280 | Packet-Level Adversarial Network Traffic Crafting Using Sequence Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on the structure of SeqGAN, we propose Attack-GAN to generate adversarial network traffic at packet level that complies with domain constraints. |
Qiumei Cheng; Shiying Zhou; Yi Shen; Dezhang Kong; Chunming Wu; | arxiv-cs.CR | 2021-03-08 |
| 281 | Improving Transformation-based Defenses Against Adversarial Examples with First-order Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this observation, we propose a method for counteracting adversarial perturbations to improve adversarial robustness. |
Haimin Zhang; Min Xu; | arxiv-cs.CV | 2021-03-08 |
| 282 | Consistency Regularization for Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate data augmentation (DA) techniques to address the issue. |
JIHOON TACK et. al. | arxiv-cs.LG | 2021-03-08 |
| 283 | Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Experimental results in MNIST SVHN and CIFAR-10 datasets show that the proposed method doesn’t rely on obfuscated gradients and achieves better global adversarial robustness generalization performance than the adversarially trained state-of-the-art CNNs. |
Desheng Wang; Weidong Jin; Yunpu Wu; Aamir Khan; | arxiv-cs.CV | 2021-03-07 |
| 284 | Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we reveal that normal examples (NEs) are insensitive to the fluctuations occurring at the highly-curved region of the decision boundary, while AEs typically designed over one single domain (mostly spatial domain) exhibit exorbitant sensitivity on such fluctuations. |
Jinyu Tian; Jiantao Zhou; Yuanman Li; Jia Duan; | arxiv-cs.LG | 2021-03-07 |
| 285 | Learning Cycle-Consistent Cooperative Networks Via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper studies the unsupervised cross-domain translation problem by proposing a generative framework, in which the probability distribution of each domain is represented by a generative cooperative network that consists of an energy-based model and a latent variable model. |
Jianwen Xie; Zilong Zheng; Xiaolin Fang; Song-Chun Zhu; Ying Nian Wu; | arxiv-cs.CV | 2021-03-07 |
| 286 | ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel implicit method to learn spatial correspondence among blurry frames in the feature space. |
DONGXU LI et. al. | arxiv-cs.CV | 2021-03-06 |
| 287 | Efficient Continual Adaptation 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; Lawrence Carin; Piyush Rai; | arxiv-cs.LG | 2021-03-06 |
| 288 | Spectral Tensor Train Parameterization of Deep Learning Layers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. |
ANTON OBUKHOV et. al. | arxiv-cs.LG | 2021-03-06 |
| 289 | High Perceptual Quality Image Denoising with A Posterior Sampling CGAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose a different perspective, aiming to produce sharp and visually pleasing denoised images that are still faithful to their clean sources. |
Guy Ohayon; Theo Adrai; Gregory Vaksman; Michael Elad; Peyman Milanfar; | arxiv-cs.CV | 2021-03-06 |
| 290 | Anomaly Detection and Automatic Labeling for Solar Cell Quality Inspection Based on Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this manuscript, a pipeline to develop an inspection system for defect detection of solar cells is proposed. |
Balzategui Julen; Eciolaza Luka; Maestro-Watson Daniel; | arxiv-cs.CV | 2021-03-05 |
| 291 | Contrastive Disentanglement in Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by contrastive learning (CL), this paper, froma new perspective, proposes contrastive disentanglement ingenerative adversarial networks (CD-GAN). |
Lili Pan; Peijun Tang; Zhiyong Chen; Zenglin Xu; | arxiv-cs.CV | 2021-03-05 |
| 292 | ASC-Net : Adversarial-based Selective Network for Unsupervised Anomaly Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a neural network framework, utilizing adversarial learning to partition an image into two cuts, with one cut falling into a reference distribution provided by the user. |
Raunak Dey; Yi Hong; | arxiv-cs.CV | 2021-03-05 |
| 293 | Anycost GANs for Interactive Image Synthesis and Editing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we take inspirations from modern rendering software and propose Anycost GAN for interactive natural image editing. |
Ji Lin; Richard Zhang; Frieder Ganz; Song Han; Jun-Yan Zhu; | arxiv-cs.CV | 2021-03-04 |
| 294 | Learning in Matrix Games Can Be Arbitrarily Complex Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we show that, in a strong sense, this dynamic complexity is inherent to games. |
Gabriel P. Andrade; Rafael Frongillo; Georgios Piliouras; | arxiv-cs.LG | 2021-03-04 |
| 295 | A Novel Application of Image-to-Image Translation: Chromosome Straightening Framework By Learning from A Single Image Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the flaws in the geometric algorithms, we propose a novel framework based on image-to-image translation to learn a pertinent mapping dependence for synthesizing straightened chromosomes with uninterrupted banding patterns and preserved details. In addition, to avoid the pitfall of deficient input chromosomes, we construct an augmented dataset using only one single curved chromosome image for training models. |
SIFAN SONG et. al. | arxiv-cs.CV | 2021-03-04 |
| 296 | MOGAN: Morphologic-structure-aware Generative Learning from A Single Image Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, this work introduces a MOrphologic-structure-aware Generative Adversarial Network named MOGAN that produces random samples with diverse appearances and reliable structures based on only one image. |
Jinshu Chen; Qihui Xu; Qi Kang; MengChu Zhou; | arxiv-cs.CV | 2021-03-04 |
| 297 | Robustness Evaluation of Stacked Generative Adversarial Networks Using Metamorphic Testing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to assess the robustness and fault-tolerance capability of the StackGAN-v2 model by introducing variations in the training data. |
HYEJIN PARK et. al. | arxiv-cs.SE | 2021-03-04 |
| 298 | Defending Medical Image Diagnostics Against Privacy Attacks Using Generative Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast to most recent work in privacy-aware ML that has been focused on model alteration and post-processing steps, we propose here a novel and complementary scheme that enhances the security of medical data by controlling the data sharing process. |
William Paul; Yinzhi Cao; Miaomiao Zhang; Phil Burlina; | arxiv-cs.CR | 2021-03-04 |
| 299 | Teachers Do More Than Teach: Compressing Image-to-Image Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to address these issues by introducing a teacher network that provides a search space in which efficient network architectures can be found, in addition to performing knowledge distillation. |
QING JIN et. al. | arxiv-cs.CV | 2021-03-04 |
| 300 | Towards Evaluating The Robustness of Deep Diagnostic Models By Adversarial Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we evaluate the robustness of deep diagnostic models by adversarial attack. |
Mengting Xu; Tao Zhang; Zhongnian Li; Mingxia Liu; Daoqiang Zhang; | arxiv-cs.CV | 2021-03-04 |
| 301 | SpectralDefense: Detecting Adversarial Attacks on CNNs in The Fourier Domain Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show how analysis in the Fourier domain of input images and feature maps can be used to distinguish benign test samples from adversarial images. |
Paula Harder; Franz-Josef Pfreundt; Margret Keuper; Janis Keuper; | arxiv-cs.CV | 2021-03-04 |
| 302 | Gradient-Guided Dynamic Efficient Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a response to the inefficiency, we propose the Dynamic Efficient Adversarial Training (DEAT), which gradually increases the adversarial iteration during training. |
Fu Wang; Yanghao Zhang; Yanbin Zheng; Wenjie Ruan; | arxiv-cs.LG | 2021-03-04 |
| 303 | Hard-label Manifolds: Unexpected Advantages of Query Efficiency for Finding On-manifold Adversarial Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that query efficiency in the zeroth-order setting is connected to an adversary’s traversal through the data manifold. |
Washington Garcia; Pin-Yu Chen; Somesh Jha; Scott Clouse; Kevin R. B. Butler; | arxiv-cs.LG | 2021-03-04 |
| 304 | Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a learning-based approach for denoising raw videos captured under low lighting conditions. |
Avinash Paliwal; Libing Zeng; Nima Khademi Kalantari; | arxiv-cs.CV | 2021-03-04 |
| 305 | Sparsity Aware Normalization for GANs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we analyze the popular spectral normalization scheme, find a significant drawback and introduce sparsity aware normalization (SAN), a new alternative approach for stabilizing GAN training. |
Idan Kligvasser; Tomer Michaeli; | arxiv-cs.CV | 2021-03-03 |
| 306 | SVMax: A Feature Embedding Regularizer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we penalize inferior network activations — feature embeddings — which in turn regularize the network’s weights implicitly. |
Ahmed Taha; Alex Hanson; Abhinav Shrivastava; Larry Davis; | arxiv-cs.CV | 2021-03-03 |
| 307 | A Robust Adversarial Network-Based End-to-End Communications System With Strong Generalization Ability Against Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel defensive mechanism based on a generative adversarial network (GAN) framework to defend against adversarial attacks in end-to-end communications systems. |
Yudi Dong; Huaxia Wang; Yu-Dong Yao; | arxiv-cs.LG | 2021-03-03 |
| 308 | House-GAN++: Generative Adversarial Layout Refinement Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel generative adversarial layout refinement network for automated floorplan generation. |
NELSON NAUATA et. al. | arxiv-cs.CV | 2021-03-03 |
| 309 | Vanishing Twin GAN: How Training A Weak Generative Adversarial Network Can Improve Semi-supervised Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose the Vanishing Twin GAN. |
Saman Motamed; Farzad Khalvati; | arxiv-cs.CV | 2021-03-03 |
| 310 | IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, we propose a deep generative model that resolves this problem by automatically learning an accurate mapping and generating diverse cellular unit cells conditioned on desired properties (i.e., Young’s modulus and Poisson’s ratio). |
Jun Wang; Wei Chen; Mark Fuge; Rahul Rai; | arxiv-cs.CE | 2021-03-03 |
| 311 | Structure-Preserving Progressive Low-rank Image Completion for Defending Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose to develop a structure-preserving progressive low-rank image completion (SPLIC) method to remove unneeded texture details from the input images and shift the bias of deep neural networks towards global object structures and semantic cues. |
Zhiqun Zhao; Hengyou Wang; Hao Sun; Zhihai He; | arxiv-cs.CV | 2021-03-03 |
| 312 | Shift Invariance Can Reduce Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show that the margin can only depend on the DC component of the signals. |
Songwei Ge; Vasu Singla; Ronen Basri; David Jacobs; | arxiv-cs.LG | 2021-03-03 |
| 313 | Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a new approach for synthesizing a novel street-view panorama given an overhead satellite image. |
Yujiao Shi; Dylan Campbell; Xin Yu; Hongdong Li; | arxiv-cs.CV | 2021-03-02 |
| 314 | A Spectral Enabled GAN for Time Series Data Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Time dependent data is a main source of information in today’s data driven world. Generating this type of data though has shown its challenges and made it an interesting research … |
Kaleb E. Smith; Anthony O. Smith; | arxiv-cs.LG | 2021-03-02 |
| 315 | Deblurring Processor for Motion-Blurred Faces Based on Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to achieve this goal, a deblurring method for motion-blurred facial image signals based on generative adversarial networks(GANs) is proposed. |
Shiqing Fan; Ye Luo; | arxiv-cs.CV | 2021-03-02 |
| 316 | ActiveGuard: An Active DNN IP Protection Technique Via Adversarial Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose an active DNN IP protection method based on adversarial examples against DNN piracy, named ActiveGuard. |
MINGFU XUE et. al. | arxiv-cs.CR | 2021-03-02 |
| 317 | Evaluating The Robustness of Geometry-Aware Instance-Reweighted Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this technical report, we evaluate the adversarial robustness of a very recent method called Geometry-aware Instance-reweighted Adversarial Training[7]. |
Dorjan Hitaj; Giulio Pagnotta; Iacopo Masi; Luigi V. Mancini; | arxiv-cs.LG | 2021-03-02 |
| 318 | Fixing Data Augmentation to Improve Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on both heuristics-driven and data-driven augmentations as a means to reduce robust overfitting. |
SYLVESTRE-ALVISE REBUFFI et. al. | arxiv-cs.CV | 2021-03-02 |
| 319 | A Survey On Universal Adversarial Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: With the focus on UAP against deep classifiers, this survey summarizes the recent progress on universal adversarial attacks, discussing the challenges from both the attack and defense sides, as well as the reason for the existence of UAP. |
CHAONING ZHANG et. al. | arxiv-cs.LG | 2021-03-02 |
| 320 | Group-wise Inhibition Based Feature Regularization for Robust Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In our method, we propose to dynamically suppress significant activation values of CNN by group-wise inhibition, but not fixedly or randomly handle them when training. |
Haozhe Liu; Haoqian Wu; Weicheng Xie; Feng Liu; Linlin Shen; | arxiv-cs.CV | 2021-03-02 |
| 321 | On The Fairness of Generative Adversarial Networks (GANs) Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we analyze and highlight fairness concerns of GANs model. |
Patrik Joslin Kenfack; Daniil Dmitrievich Arapovy; Rasheed Hussain; S. M. Ahsan Kazmi; Adil Mehmood Khan; | arxiv-cs.LG | 2021-03-01 |
| 322 | Generative Adversarial Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce the GANsformer, a novel and efficient type of transformer, and explore it for the task of visual generative modeling. |
Drew A. Hudson; C. Lawrence Zitnick; | arxiv-cs.CV | 2021-03-01 |
| 323 | Smoothness Analysis of Loss Functions of Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we analyze the smoothness of the loss function of adversarial training for binary linear classification and for general cases considering the dependence. |
Sekitoshi Kanai; Masanori Yamada; Hiroshi Takahashi; Yuki Yamanaka; Yasutoshi Ida; | arxiv-cs.LG | 2021-03-01 |
| 324 | A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we propose a multiclass boosting framework to ensure adversarial robustness. |
Jacob Abernethy; Pranjal Awasthi; Satyen Kale; | arxiv-cs.LG | 2021-03-01 |
| 325 | Brain Programming Is Immune to Adversarial Attacks: Towards Accurate and Robust Image Classification Using Symbolic Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we perform a comparative study of the effects of AA on the complex problem of art media categorization, which involves a sophisticated analysis of features to classify a fine collection of artworks. |
Gerardo Ibarra-Vazquez; Gustavo Olague; Mariana Chan-Ley; Cesar Puente; Carlos Soubervielle-Montalvo; | arxiv-cs.CV | 2021-03-01 |
| 326 | Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast, we introduce a simple and efficient “convolutional normalization” method that can fully exploit the convolutional structure in the Fourier domain and serve as a simple plug-and-play module to be conveniently incorporated into any ConvNets. |
SHENG LIU et. al. | arxiv-cs.CV | 2021-02-28 |
| 327 | Training Generative Adversarial Networks in One Stage Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate a general training scheme that enables training GANs efficiently in only one stage. |
CHENGCHAO SHEN et. al. | arxiv-cs.CV | 2021-02-28 |
| 328 | Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Such a coordinated framework enables us to focus on lower-complexity and more data-efficient sub-problems, effectively stabilizing training and improving convergence. |
Tianlong Chen; Yu Cheng; Zhe Gan; Jingjing Liu; Zhangyang Wang; | arxiv-cs.LG | 2021-02-28 |
| 329 | Unsupervised Domain Adaptation for Cross-Subject Few-Shot Neurological Symptom Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces an unsupervised domain adaptation approach based on adversarial networks to enable few-shot, cross-subject epileptic seizure detection. |
Bingzhao Zhu; Mahsa Shoaran; | arxiv-cs.LG | 2021-02-28 |
| 330 | Model-Agnostic Defense for Lane Detection Against Adversarial Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a modular lane verification system that can catch such threats before the autonomous driving system is misled while remaining agnostic to the particular lane detection model. |
Henry Xu; An Ju; David Wagner; | arxiv-cs.CV | 2021-02-28 |
| 331 | Tiny Adversarial Mulit-Objective Oneshot Neural Architecture Search Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a multi-objective oneshot network architecture search (NAS) algorithm to obtain the best trade-off networks in terms of the adversarial accuracy, the clean accuracy and the model size. |
Guoyang Xie; Jinbao Wang; Guo Yu; Feng Zheng; Yaochu Jin; | arxiv-cs.LG | 2021-02-27 |
| 332 | A Brief Introduction to Generative Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce and motivate generative modeling as a central task for machine learning and provide a critical view of the algorithms which have been proposed for solving this task. |
Alex Lamb; | arxiv-cs.LG | 2021-02-27 |
| 333 | RA-GCN: Graph Convolutional Network for Disease Prediction Problems with Imbalanced Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Re-weighted Adversarial Graph Convolutional Network (RA-GCN) to enhance the performance of the graph-based classifier and prevent it from emphasizing the samples of any particular class. |
Mahsa Ghorbani; Anees Kazi; Mahdieh Soleymani Baghshah; Hamid R. Rabiee; Nassir Navab; | arxiv-cs.LG | 2021-02-27 |
| 334 | End-to-end Uncertainty-based Mitigation of Adversarial Attacks to Automated Lane Centering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an end-to-end approach that addresses the impact of adversarial attacks throughout perception, planning, and control modules. |
RUOCHEN JIAO et. al. | arxiv-cs.RO | 2021-02-27 |
| 335 | Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we design an uncertainty-aware domain adaptation network (UaDAN) that introduces conditional adversarial learning to align well-aligned and poorly-aligned samples separately in different manners. |
Dayan Guan; Jiaxing Huang; Aoran Xiao; Shijian Lu; Yanpeng Cao; | arxiv-cs.CV | 2021-02-27 |
| 336 | Continuous Face Aging Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose the continuous face aging generative adversarial networks (CFA-GAN). |
Seogkyu Jeon; Pilhyeon Lee; Kibeom Hong; Hyeran Byun; | arxiv-cs.CV | 2021-02-26 |
| 337 | Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel zero-shot learning approach, GAN-CST, based on class knowledge to visual feature learning to tackle the problem. |
CHENG XIE et. al. | arxiv-cs.CV | 2021-02-26 |
| 338 | Zero-Shot Learning Based on Knowledge Sharing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce knowledge sharing (KS) to enrich the representation of semantic features. |
Zeng Ting; Xiang Hongxin; Xie Cheng; Yang Yun; Liu Qing; | arxiv-cs.CV | 2021-02-26 |
| 339 | Partitioned Graph Convolution Using Adversarial and Regression Networks for Road Travel Speed Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a framework for predicting road segment travel speed histograms for dataless edges, based on a latent representation generated by an adversarially regularized convolutional network. |
Jakob Meldgaard Kjær; Lasse Kristensen; Mads Alberg Christensen; | arxiv-cs.LG | 2021-02-26 |
| 340 | What Doesn’t Kill You Makes You Robust(er): Adversarial Training Against Poisons and Backdoors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we extend the adversarial training framework to instead defend against (training-time) poisoning and backdoor attacks. |
JONAS GEIPING et. al. | arxiv-cs.LG | 2021-02-26 |
| 341 | NEUROSPF: A Tool for The Symbolic Analysis of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks. |
Muhammad Usman; Yannic Noller; Corina Pasareanu; Youcheng Sun; Divya Gopinath; | arxiv-cs.LG | 2021-02-26 |
| 342 | Local Stochastic Gradient Descent Ascent: Convergence Analysis and Communication Efficiency Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Motivated by large scale minimax learning problems, such as adversarial robust learning and training generative adversarial networks (GANs), we propose local Stochastic Gradient Descent Ascent (local SGDA), where the primal and dual variables can be trained locally and averaged periodically to significantly reduce the number of communications. |
Yuyang Deng; Mehrdad Mahdavi; | arxiv-cs.LG | 2021-02-25 |
| 343 | Deep Adversarial Learning on Google Home Devices Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To cope with that, deep adversarial learning approaches can be used to build black-box countermeasures altering the network traffic (e.g., via packet padding) and its statistical information. |
Andrea Ranieri; Davide Caputo; Luca Verderame; Alessio Merlo; Luca Caviglione; | arxiv-cs.CR | 2021-02-25 |
| 344 | Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address this critical issue by introducing a framework for analyzing robustness of the learning algorithm w.r.t varying quality in the image input for autonomous driving. |
YU SHEN et. al. | arxiv-cs.CV | 2021-02-25 |
| 345 | Interpreting The Latent Space of Generative Adversarial Networks Using Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: With great progress in the development of Generative Adversarial Networks (GANs), in recent years, the quest for insights in understanding and manipulating the latent space of GAN … |
TOAN PHAM VAN et. al. | arxiv-cs.LG | 2021-02-24 |
| 346 | Estimation of Continuous Blood Pressure from PPG Via A Federated Learning Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We train our framework across distributed models and data sources to mimic a large-scale distributed collaborative learning experiment that could be implemented across low-cost wearables. |
Eoin Brophy; Maarten De Vos; Geraldine Boylan; Tomas Ward; | arxiv-cs.LG | 2021-02-24 |
| 347 | AniGAN: Style-Guided Generative Adversarial Networks for Unsupervised Anime Face Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework to translate a portrait photo-face into an anime appearance. |
BING LI et. al. | arxiv-cs.CV | 2021-02-24 |
| 348 | Disentangling Brain Heterogeneity Via Semi-supervised Deep-learning and MRI: Dimensional Representations of Alzheimer’s Disease Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe and validate Smile-GAN (SeMI-supervised cLustEring-Generative Adversarial Network), a novel semi-supervised deep-clustering method, which dissects neuroanatomical heterogeneity, enabling identification of disease subtypes via their imaging signatures relative to controls. |
ZHIJIAN YANG et. al. | arxiv-cs.LG | 2021-02-24 |
| 349 | Identifying Untrustworthy Predictions in Neural Networks By Geometric Gradient Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a geometric gradient analysis (GGA) to improve the identification of untrustworthy predictions without retraining of a given model. |
LEO SCHWINN et. al. | arxiv-cs.LG | 2021-02-24 |
| 350 | Multiplicative Reweighting for Robust Neural Network Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the setting of learning with expert advice, where multiplicative weights (MW) updates were recently shown to be robust to moderate adversarial corruptions, we propose to use MW for reweighting examples during neural networks optimization. |
Noga Bar; Tomer Koren; Raja Giryes; | arxiv-cs.LG | 2021-02-24 |
| 351 | Graphfool: Targeted Label Adversarial Attack on Graph Embedding Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, in this paper, we propose Graphfool, a novel targeted label adversarial attack on graph embedding. |
JINYIN CHEN et. al. | arxiv-cs.LG | 2021-02-24 |
| 352 | Robust SleepNets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we investigate eye closedness detection to prevent vehicle accidents related to driver disengagements and driver drowsiness. |
Yigit Alparslan; Edward Kim; | arxiv-cs.CV | 2021-02-24 |
| 353 | Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To guarantee both the quality and the diversity, 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; | arxiv-cs.LG | 2021-02-23 |
| 354 | Learning to Drop Points for LiDAR Scan Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a novel framework based on generative adversarial networks to synthesize realistic LiDAR data as an improved 2D representation. |
Kazuto Nakashima; Ryo Kurazume; | arxiv-cs.CV | 2021-02-23 |
| 355 | Non-Singular Adversarial Robustness of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights. |
Yu-Lin Tsai; Chia-Yi Hsu; Chia-Mu Yu; Pin-Yu Chen; | arxiv-cs.LG | 2021-02-23 |
| 356 | Adversarial Robustness with Non-uniform Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose using characteristics of the empirical data distribution, both on correlations between the features and the importance of the features themselves. |
Ecenaz Erdemir; Jeffrey Bickford; Luca Melis; Sergul Aydore; | arxiv-cs.LG | 2021-02-23 |
| 357 | Automated Discovery of Adaptive Attacks on Adversarial Defenses Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on this observation, we present an extensible framework that defines a search space over these reusable building blocks and automatically discovers an effective attack on a given model with an unknown defense by searching over suitable combinations of these blocks. |
Chengyuan Yao; Pavol Bielik; Petar Tsankov; Martin Vechev; | arxiv-cs.LG | 2021-02-23 |
| 358 | Enhancing Model Robustness By Incorporating Adversarial Knowledge Into Semantic Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, we propose AdvGraph, a novel defense which enhances the robustness of Chinese-based NLP models by incorporating adversarial knowledge into the semantic representation of the input. |
JINFENG LI et. al. | arxiv-cs.CL | 2021-02-23 |
| 359 | Adversarial Examples Detection Beyond Image Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To detect both few-perturbation attacks and large-perturbation attacks, we propose a method beyond image space by a two-stream architecture, in which the image stream focuses on the pixel artifacts and the gradient stream copes with the confidence artifacts. |
KEJIANG CHEN et. al. | arxiv-cs.CV | 2021-02-23 |
| 360 | Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The student model can achieve 95.42% accuracy on CIFAR-10 and 77.05% accuracy on CIFAR-100 without any original training data. |
Xiaoyang Qu; Jianzong Wang; Jing Xiao; | arxiv-cs.LG | 2021-02-23 |
| 361 | Decision Power of Weak Asynchronous Models of Distributed Computing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we present an algorithm for majority that works for all bounded-degree networks under adversarial schedulers, i.e. even if the scheduler must only satisfy that every node makes a move infinitely often, and prove that no such algorithm can work for arbitrary networks. |
Philipp Czerner; Roland Guttenberg; Martin Helfrich; Javier Esparza; | arxiv-cs.FL | 2021-02-23 |
| 362 | Distributional Reinforcement Learning for MmWave Communications with Intelligent Reflectors on A UAV IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a novel framework is proposed to enable air-to-ground channel modeling over millimeter wave (mmWave) frequencies in an unmanned aerial vehicle (UAV) wireless network. |
Qianqian Zhang; Aidin Ferdowsi; Walid Saad; | arxiv-cs.IT | 2021-02-22 |
| 363 | Investigating Deep Neural Structures and Their Interpretability in The Domain of Voice Conversion Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the study reported here, we investigated the interpretability of state-of-the-art implementations of non-parallel GANs in the domain of VC. |
Samuel J. Broughton; Md Asif Jalal; Roger K. Moore; | arxiv-cs.SD | 2021-02-22 |
| 364 | Anyone GAN Sing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a method to synthesize the singing voice of a person using a Convolutional Long Short-term Memory (ConvLSTM) based GAN optimized using the Wasserstein loss function. |
Shreeviknesh Sankaran; Sukavanan Nanjundan; G. Paavai Anand; | arxiv-cs.SD | 2021-02-22 |
| 365 | Residual-Aided End-to-End Learning of Communication System Without Known Channel Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate these two problems, we propose a residual aided GAN (RA-GAN) based training scheme in this paper. |
Hao Jiang; Shuangkaisheng Bi; Linglong Dai; | arxiv-cs.IT | 2021-02-22 |
| 366 | Resilience of Bayesian Layer-Wise Explanations Under Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the problem of the stability of saliency-based explanations of Neural Network predictions under adversarial attacks in a classification task. |
Ginevra Carbone; Guido Sanguinetti; Luca Bortolussi; | arxiv-cs.LG | 2021-02-22 |
| 367 | On The Robustness of Randomized Classifiers to Adversarial Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The second contribution presents a yet simple but efficient noise injection method to design robust randomized classifiers. |
RAFAEL PINOT et. al. | arxiv-cs.LG | 2021-02-22 |
| 368 | Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the proposed ASLNet, we introduce the adversarial learning strategy to explicitly model the shape constraints, as well as a CNN shape regularizer to strengthen the embedding of shape features. |
LEI DING et. al. | arxiv-cs.CV | 2021-02-22 |
| 369 | Do Generative Models Know Disentanglement? Contrastive Learning Is All You Need Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an unsupervised and model-agnostic method: Disentanglement via Contrast (DisCo) in the Variation Space. |
Xuanchi Ren; Tao Yang; Yuwang Wang; Wenjun Zeng; | arxiv-cs.CV | 2021-02-21 |
| 370 | The Effects of Image Distribution and Task on Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an adaptation to the area under the curve (AUC) metric to measure the adversarial robustness of a model over a particular $\epsilon$-interval $[\epsilon_0, \epsilon_1]$ (interval of adversarial perturbation strengths) that facilitates unbiased comparisons across models when they have different initial $\epsilon_0$ performance. |
Owen Kunhardt; Arturo Deza; Tomaso Poggio; | arxiv-cs.LG | 2021-02-21 |
| 371 | Augmenting High-dimensional Nonlinear Optimization with Conditional GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes generative models as a complement to optimization algorithms to improve performance in problems with high dimensionality. |
Pouya Rezazadeh Kalehbasti; Michael D. Lepech; Samarpreet Singh Pandher; | arxiv-cs.NE | 2021-02-20 |
| 372 | Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a distributed approach to train deep convolutional generative adversarial neural network (DC-CGANs) models. |
Massimiliano Lupo Pasini; Vittorio Gabbi; Junqi Yin; Simona Perotto; Nouamane Laanait; | arxiv-cs.CV | 2021-02-20 |
| 373 | Analyzing Overfitting Under Class Imbalance in Neural Networks for Image Segmentation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we provide new insights on the problem of overfitting under class imbalance by inspecting the network behavior. |
Zeju Li; Konstantinos Kamnitsas; Ben Glocker; | arxiv-cs.CV | 2021-02-20 |
| 374 | Conditional Adversarial Networks for Multi-Domain Text Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose conditional adversarial networks (CANs), a framework that explores the relationship between the shared features and the label predictions to impose more discriminability to the shared features, for multi-domain text classification (MDTC). |
Yuan Wu; Diana Inkpen; Ahmed El-Roby; | arxiv-cs.LG | 2021-02-19 |
| 375 | Effective and Efficient Vote Attack on Capsule Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate the adversarial robustness of CapsNets, especially how the inner workings of CapsNets change when the output capsules are attacked. |
Jindong Gu; Baoyuan Wu; Volker Tresp; | arxiv-cs.CV | 2021-02-19 |
| 376 | One Shot Audio to Animated Video Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel method OneShotAu2AV to generate an animated video of arbitrary length using an audio clip and a single unseen image of a person as an input. |
NEERAJ KUMAR et. al. | arxiv-cs.CV | 2021-02-18 |
| 377 | DINO: A Conditional Energy-Based GAN for Domain Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an alternative method for conditioning and present a new framework, where two networks are simultaneously trained, in a supervised manner, to perform domain translation in opposite directions. |
Konstantinos Vougioukas; Stavros Petridis; Maja Pantic; | arxiv-cs.LG | 2021-02-18 |
| 378 | Composable Generative Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper focuses on synthetic data generation models with privacy preserving applications in mind. |
Johan Leduc; Nicolas Grislain; | arxiv-cs.LG | 2021-02-18 |
| 379 | Random Projections for Improved Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose two training techniques for improving the robustness of Neural Networks to adversarial attacks, i.e. manipulations of the inputs that are maliciously crafted to fool networks into incorrect predictions. |
Ginevra Carbone; Guido Sanguinetti; Luca Bortolussi; | arxiv-cs.LG | 2021-02-18 |
| 380 | Causal Inference Q-Network: Toward Resilient Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider a generative DRL framework training with an auxiliary task of observational interferences such as artificial noises. |
Chao-Han Huck Yang; I-Te Danny Hung; Yi Ouyang; Pin-Yu Chen; | arxiv-cs.LG | 2021-02-18 |
| 381 | An Enhanced Adversarial Network with Combined Latent Features for Spatio-Temporal Facial Affect Estimation in The Wild Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper addresses these shortcomings by proposing a novel model that efficiently extracts both spatial and temporal features of the data by means of its enhanced temporal modelling based on latent features. |
Decky Aspandi; Federico Sukno; Björn Schuller; Xavier Binefa; | arxiv-cs.CV | 2021-02-17 |
| 382 | DO-GAN: A Double Oracle Framework for Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new approach to train Generative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discriminator oracles. |
AYE PHYU PHYU AUNG et. al. | arxiv-cs.LG | 2021-02-17 |
| 383 | Evolving GAN Formulations for Higher Quality Image Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a new technique called TaylorGAN for improving GANs by discovering customized loss functions for each of its two networks. |
Santiago Gonzalez; Mohak Kant; Risto Miikkulainen; | arxiv-cs.NE | 2021-02-17 |
| 384 | Towards Adversarial-Resilient Deep Neural Networks for False Data Injection Attack Detection in Power Grids Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we evaluate the vulnerability of DNNs used for FDIA detection through adversarial attacks and study the defensive approaches. |
Jiangnan Li; Yingyuan Yang; Jinyuan Stella Sun; Kevin Tomsovic; Hairong Qi; | arxiv-cs.CR | 2021-02-17 |
| 385 | Improving Hierarchical Adversarial Robustness of Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to better tackle this important problematic, we introduce the concept of hierarchical adversarial robustness. |
Avery Ma; Aladin Virmaux; Kevin Scaman; Juwei Lu; | arxiv-cs.LG | 2021-02-17 |
| 386 | Complex Momentum for Learning in Games Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We give theoretical motivation for our method by proving convergence on bilinear zero-sum games for simultaneous and alternating updates. |
Jonathan Lorraine; David Acuna; Paul Vicol; David Duvenaud; | arxiv-cs.LG | 2021-02-16 |
| 387 | CTAB-GAN: Effective Table Data Synthesizing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop CTAB-GAN, a novel conditional table GAN architecture that can effectively model diverse data types, including a mix of continuous and categorical variables. |
Zilong Zhao; Aditya Kunar; Hiek Van der Scheer; Robert Birke; Lydia Y. Chen; | arxiv-cs.LG | 2021-02-16 |
| 388 | Adversarial Targeted Forgetting in Regularization and Generative Based Continual Learning Models Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Continual (or incremental) learning approaches are employed when additional knowledge or tasks need to be learned from subsequent batches or from streaming data. |
Muhammad Umer; Robi Polikar; | arxiv-cs.LG | 2021-02-16 |
| 389 | WGAN with An Infinitely Wide Generator Has No Spurious Stationary Points Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show that GANs with a 2-layer infinite-width generator and a 2-layer finite-width discriminator trained with stochastic gradient ascent-descent have no spurious stationary points. |
Albert No; Taeho Yoon; Se-Hyeon Kwon; Ernest K. Ryu; | arxiv-cs.LG | 2021-02-15 |
| 390 | MITNet: GAN Enhanced Magnetic Induction Tomography Based on Complex CNN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a generative adversarial network (GAN) enhanced MIT technique, named MITNet, based on a complex convolutional neural network (CNN). |
ZUOHUI CHEN et. al. | arxiv-cs.CV | 2021-02-15 |
| 391 | Generation For Adaption: A GAN-Based Approach for 3D Domain Adaption with Point Cloud Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Unsupervised domain adaptation (UDA) seeks to overcome such a problem without target domain labels.Instead of aligning features between source data and target data,we propose a method that use a Generative adversarial network to generate synthetic data from the source domain so that the output is close to the target domain.Experiments show that our approach performs better than other state-of-the-art UDA methods in three popular 3D object/scene datasets (i.e., ModelNet, ShapeNet and ScanNet) for cross-domain 3D objects classification. |
Junxuan Huang; Junsong Yuan; Chunming Qiao; | arxiv-cs.CV | 2021-02-15 |
| 392 | And/or Trade-off in Artificial Neurons: Impact on Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Our idea to increase adversarial resilience starts with the observation that artificial neurons can be divided in two broad categories: AND-like neurons and OR-like neurons. |
Alessandro Fontana; | arxiv-cs.LG | 2021-02-15 |
| 393 | 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; David Jacobs; Soheil Feizi; | arxiv-cs.LG | 2021-02-15 |
| 394 | CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate the effects of adversarial attacks, we propose a novel purification model called CAP-GAN. |
Mingu Kang; Trung Quang Tran; Seungju Cho; Daeyoung Kim; | arxiv-cs.LG | 2021-02-14 |
| 395 | Multi-class Classification Based Anomaly Detection of Insider Activities Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate the effect of skewed class distribution and prove the potential of multinomial classification algorithms for insider threat detection, we propose an approach that combines generative model with supervised learning to perform multi-class classification using deep learning. |
R G Gayathri; Atul Sajjanhar; Yong Xiang; Xingjun Ma; | arxiv-cs.CR | 2021-02-14 |
| 396 | Naturalizing Neuromorphic Vision Event Streams Using GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we methodically apply the Pix2Pix network to naturalize the event stream from spike-converted CIFAR-10 and Linnaeus 5 datasets. |
Dennis Robey; Wesley Thio; Herbert Iu; Jason Eshraghian; | arxiv-cs.CV | 2021-02-14 |
| 397 | TransGAN: Two Transformers Can Make One Strong GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Driven by that curiosity, we conduct the first pilot study in building a GAN \textbf{completely free of convolutions}, using only pure transformer-based architectures. |
Yifan Jiang; Shiyu Chang; Zhangyang Wang; | arxiv-cs.CV | 2021-02-14 |
| 398 | OntoZSL: Ontology-enhanced Zero-shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore richer and more competitive prior knowledge to model the inter-class relationship for ZSL via ontology-based knowledge representation and semantic embedding. |
YUXIA GENG et. al. | arxiv-cs.AI | 2021-02-14 |
| 399 | Adversarial Attack on Network Embeddings Via Supervised Network Poisoning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study network embedding algorithms from an adversarial point of view and observe the effect of poisoning the network on downstream tasks. |
Viresh Gupta; Tanmoy Chakraborty; | arxiv-cs.LG | 2021-02-14 |
| 400 | Cross-modal Adversarial Reprogramming Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we broaden the scope of adversarial reprogramming beyond the data modality of the original task. |
PAARTH NEEKHARA et. al. | arxiv-cs.AI | 2021-02-14 |
| 401 | Guided Interpolation for Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, to mitigate this issue, we propose the guided interpolation framework (GIF): in each epoch, the GIF employs the previous epoch’s meta information to guide the data’s interpolation. |
CHEN CHEN et. al. | arxiv-cs.LG | 2021-02-14 |
| 402 | Exploring Adversarial Robustness of Deep Metric Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We take a first step towards training robust DML models and tackle the primary challenge of the metric losses being dependent on the samples in a mini-batch, unlike standard losses that only depend on the specific input-output pair. |
Thomas Kobber Panum; Zi Wang; Pengyu Kan; Earlence Fernandes; Somesh Jha; | arxiv-cs.LG | 2021-02-14 |
| 403 | Wasserstein Proximal of GANs IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new method for training generative adversarial networks by applying the Wasserstein-2 metric proximal on the generators. |
Alex Tong Lin; Wuchen Li; Stanley Osher; Guido Montufar; | arxiv-cs.LG | 2021-02-13 |
| 404 | Multi-class Generative Adversarial Nets for Semi-supervised Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we use various images from MNIST and Fashion-MNIST datasets to illustrate how similar images cause the GAN to generalize, leading to the poor classification of images. |
Saman Motamed; Farzad Khalvati; | arxiv-cs.CV | 2021-02-13 |
| 405 | Learning Speech-driven 3D Conversational Gestures from Video IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the first approach to automatically and jointly synthesize both the synchronous 3D conversational body and hand gestures, as well as 3D face and head animations, of a virtual character from speech input. |
IKHSANUL HABIBIE et. al. | arxiv-cs.CV | 2021-02-12 |
| 406 | Efficient Conditional GAN Transfer with Knowledge Propagation Across Classes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we introduce a new GAN transfer method to explicitly propagate the knowledge from the old classes to the new classes. |
Mohamad Shahbazi; Zhiwu Huang; Danda Pani Paudel; Ajad Chhatkuli; Luc Van Gool; | arxiv-cs.CV | 2021-02-12 |
| 407 | Universal Adversarial Perturbations Through The Lens of Deep Steganography: Towards A Fourier Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We perform task-specific and joint analysis and reveal that (a) frequency is a key factor that influences their performance based on the proposed entropy metric for quantifying the frequency distribution; (b) their success can be attributed to a DNN being highly sensitive to high-frequency content. |
Chaoning Zhang; Philipp Benz; Adil Karjauv; In So Kweon; | arxiv-cs.LG | 2021-02-12 |
| 408 | Reinforcement Learning For Data Poisoning on Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Adversarial Machine Learning has emerged as a substantial subfield of Computer Science due to a lack of robustness in the models we train along with crowdsourcing practices that enable attackers to tamper with data. |
Jacob Dineen; A S M Ahsan-Ul Haque; Matthew Bielskas; | arxiv-cs.LG | 2021-02-12 |
| 409 | Adversarial Branch Architecture Search for Unsupervised Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we propose an Adversarial Branch Architecture Search (ABAS) for UDA, to learn the auxiliary branch network from data without handcrafting. |
Luca Robbiano; Muhammad Rameez Ur Rahman; Fabio Galasso; Barbara Caputo; Fabio Maria Carlucci; | arxiv-cs.CV | 2021-02-12 |
| 410 | Adversarial Segmentation Loss for Sketch Colorization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new method for generating color images from sketches or edge maps. |
Samet Hicsonmez; Nermin Samet; Emre Akbas; Pinar Duygulu; | arxiv-cs.CV | 2021-02-11 |
| 411 | SWAGAN: A Style-based Wavelet-driven Generative Model Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we present a novel general-purpose Style and WAvelet based GAN (SWAGAN) that implements progressive generation in the frequency domain. |
Rinon Gal; Dana Cohen; Amit Bermano; Daniel Cohen-Or; | arxiv-cs.CV | 2021-02-11 |
| 412 | Deep Photo Scan: Semi-supervised Learning for Dealing with The Real-world Degradation in Smartphone Photo Scanning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve these problems, we propose a Deep Photo Scan (DPScan) based on semi-supervised learning. |
Man M. Ho; Jinjia Zhou; | arxiv-cs.CV | 2021-02-11 |
| 413 | Defuse: Harnessing Unrestricted Adversarial Examples for Debugging Models Beyond Test Accuracy Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Defuse, a method that generates novel model misclassifications, categorizes these errors into high-level model bugs, and efficiently labels and fine-tunes on the errors to correct them. |
Dylan Slack; Nathalie Rauschmayr; Krishnaram Kenthapadi; | arxiv-cs.LG | 2021-02-11 |
| 414 | Adversarially Robust Deepfake Media Detection Using Fused Convolutional Neural Network Predictions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we employ three different deep Convolutional Neural Network (CNN) models, (1) VGG16, (2) InceptionV3, and (3) XceptionNet to classify fake and real images extracted from videos. |
Sohail Ahmed Khan; Alessandro Artusi; Hang Dai; | arxiv-cs.CV | 2021-02-11 |
| 415 | Hyperbolic Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, different configurations using fully connected hyperbolic layers in the GAN, CGAN, and WGAN are tested, in what we call the HGAN, HCGAN, and HWGAN, respectively. |
Diego Lazcano; Nicolás Fredes; Werner Creixell; | arxiv-cs.LG | 2021-02-10 |
| 416 | Bayesian Inference with Certifiable Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider adversarial training of deep neural networks through the lens of Bayesian learning, and present a principled framework for adversarial training of Bayesian Neural Networks (BNNs) with certifiable guarantees. |
MATTHEW WICKER et. al. | arxiv-cs.LG | 2021-02-10 |
| 417 | Towards Certifying $\ell_\infty$ Robustness Using Neural Networks with $\ell_\infty$-dist Neurons Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we seek for a new approach to develop a theoretically principled neural network that inherently resists $\ell_\infty$ perturbations. |
Bohang Zhang; Tianle Cai; Zhou Lu; Di He; Liwei Wang; | arxiv-cs.LG | 2021-02-10 |
| 418 | SteaLTE: Private 5G Cellular Connectivity As A Service with Full-stack Wireless Steganography Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the concept of Private Cellular Connectivity as a Service (PCCaaS), where infrastructure providers deploy covert network slices known only to a subset of users. |
Leonardo Bonati; Salvatore D’Oro; Francesco Restuccia; Stefano Basagni; Tommaso Melodia; | arxiv-cs.NI | 2021-02-10 |
| 419 | Diverse Single Image Generation with Controllable Global Structure Through Self-Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We solve this problem by using attention blocks at selected scales and feeding a random Gaussian blurred image to the discriminator for training. |
Sutharsan Mahendren; Chamira Edussooriya; Ranga Rodrigo; | arxiv-cs.CV | 2021-02-09 |
| 420 | Training Federated GANs with Theoretical Guarantees: A Universal Aggregation Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new approach called Universal Aggregation, which simulates a centralized discriminator via carefully aggregating the mixture of all private discriminators. |
YIKAI ZHANG et. al. | arxiv-cs.LG | 2021-02-09 |
| 421 | Using Deep LSD to Build Operators in GANs Latent Space with Meaning in Real Space Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we propose a method to build a set of linearly independent vectors in the latent space of a GANs, which we call quasi-eigenvectors. |
J. Quetzalcoatl Toledo-Marin; James A. Glazier; | arxiv-cs.LG | 2021-02-09 |
| 422 | 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; Atılım Güneş Baydin; | arxiv-cs.LG | 2021-02-09 |
| 423 | Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we extend the work of Ilyas et al. by investigating the nature of the input patterns that give rise to these features. |
Jacob M. Springer; Melanie Mitchell; Garrett T. Kenyon; | arxiv-cs.LG | 2021-02-09 |
| 424 | Generative Models As Distributions of Functions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we abandon discretized grids and instead parameterize individual data points by continuous functions. |
Emilien Dupont; Yee Whye Teh; Arnaud Doucet; | arxiv-cs.LG | 2021-02-09 |
| 425 | Target Training Does Adversarial Training Without Adversarial Samples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Neural network classifiers are vulnerable to misclassification of adversarial samples, for which the current best defense trains classifiers with adversarial samples. However, … |
Blerta Lindqvist; | arxiv-cs.LG | 2021-02-09 |
| 426 | Detecting Localized Adversarial Examples: A Generic Approach Using Critical Region Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper,we propose a generic defense system called TaintRadar to accurately detect localized adversarial examples via analyzing critical regions that have been manipulated by attackers. |
FENGTING LI et. al. | arxiv-cs.CV | 2021-02-09 |
| 427 | Regularized Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a framework for generating samples from a probability distribution that differs from the probability distribution of the training set. |
Gabriele Di Cerbo; Ali Hirsa; Ahmad Shayaan; | arxiv-cs.LG | 2021-02-08 |
| 428 | UVTomo-GAN: An Adversarial Learning Based Approach for Unknown View X-ray Tomographic Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this set-up our goal is to recover the image and the projection angle distribution using an unsupervised adversarial learning approach. |
Mona Zehni; Zhizhen Zhao; | arxiv-cs.CV | 2021-02-08 |
| 429 | HumanACGAN: Conditional Generative Adversarial Network with Human-based Auxiliary Classifier and Its Evaluation in Phoneme Perception Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a conditional generative adversarial network (GAN) incorporating humans’ perceptual evaluations. |
YOTA UEDA et. al. | arxiv-cs.HC | 2021-02-08 |
| 430 | Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper therefore presents a complete protection framework in both black-box and white-box settings to enforce IPR protection on GANs. |
Ding Sheng Ong; Chee Seng Chan; Kam Woh Ng; Lixin Fan; Qiang Yang; | arxiv-cs.CR | 2021-02-08 |
| 431 | A Real-time Defense Against Website Fingerprinting Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Dolos, a system that modifies user network traffic in real time to successfully evade WF attacks. |
Shawn Shan; Arjun Nitin Bhagoji; Haitao Zheng; Ben Y. Zhao; | arxiv-cs.CR | 2021-02-08 |
| 432 | Benford’s Law: What Does It Say on Adversarial Images? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we investigate statistical differences between natural images and adversarial ones. |
João G. Zago; Fabio L. Baldissera; Eric A. Antonelo; Rodrigo T. Saad; | arxiv-cs.CV | 2021-02-08 |
| 433 | Exploiting Epistemic Uncertainty of The Deep Learning Models to Generate Adversarial Samples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We proposed new attack ideas based on the epistemic uncertainty of the model. |
Omer Faruk Tuna; Ferhat Ozgur Catak; M. Taner Eskil; | arxiv-cs.LG | 2021-02-08 |
| 434 | Solid Texture Synthesis Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we proposed a novel neural network-based approach for the solid texture synthesis based on generative adversarial networks, namely STS-GAN, in which the generator composed of multi-scale modules learns the internal distribution of 2D exemplar and further extends it to a 3D solid texture. |
XIN ZHAO et. al. | arxiv-cs.CV | 2021-02-07 |
| 435 | One-shot Face Reenactment Using Appearance Adaptive Normalization Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The paper proposes a novel generative adversarial network for one-shot face reenactment, which can animate a single face image to a different pose-and-expression (provided by a driving image) while keeping its original appearance. |
GUANGMING YAO et. al. | arxiv-cs.CV | 2021-02-07 |
| 436 | Black-Box Optimization Via Generative Adversarial Nets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an optimizer using generative adversarial nets (OPT-GAN) to guide search on black-box problems via estimating the distribution of optima. |
Minfang Lu; Fengyang Sun; Lin Wang; Bo Yang; Shuangrong Liu; | arxiv-cs.LG | 2021-02-07 |
| 437 | Adversarial Imaging Pipelines Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we examine and develop such an attack that deceives a specific camera ISP while leaving others intact, using the same down-stream classifier. |
Buu Phan; Fahim Mannan; Felix Heide; | arxiv-cs.CV | 2021-02-07 |
| 438 | Adversarial Example Generation with AdaBelief Optimizer and Crop Invariance Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose AdaBelief Iterative Fast Gradient Method (ABI-FGM) and Crop-Invariant attack Method (CIM) to improves the transferability of adversarial examples. |
Bo Yang; Hengwei Zhang; Yuchen Zhang; Kaiyong Xu; Jindong Wang; | arxiv-cs.CV | 2021-02-07 |
| 439 | Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the validity of DANN in domain generalization from this perspective. |
Anthony Sicilia; Xingchen Zhao; Seong Jae Hwang; | arxiv-cs.LG | 2021-02-07 |
| 440 | HGAN: Hybrid Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a simple approach to train Generative Adversarial Networks (GANs) in order to avoid a \textit {mode collapse} issue. |
Seyed Mehdi Iranmanesh; Nasser M. Nasrabadi; | arxiv-cs.CV | 2021-02-06 |
| 441 | SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A black-box spectral method is introduced for evaluating the adversarial robustness of a given machine learning (ML) model. |
WUXINLIN CHENG et. al. | arxiv-cs.LG | 2021-02-06 |
| 442 | Transductive Zero-Shot Learning By Decoupled Feature Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address zero-shot learning (ZSL), the problem of recognizing categories for which no labeled visual data are available during training. |
Federico Marmoreo; Jacopo Cavazza; Vittorio Murino; | arxiv-cs.CV | 2021-02-05 |
| 443 | Unsupervised Novel View Synthesis from A Single Image Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work aims at relaxing this assumption enabling training of conditional generative model for novel view synthesis in a completely unsupervised manner. |
Pierluigi Zama Ramirez; Alessio Tonioni; Federico Tombari; | arxiv-cs.CV | 2021-02-05 |
| 444 | Real-World Super-Resolution of Face-Images from Surveillance Cameras Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this problem, we propose a novel framework for generation of realistic LR/HR training pairs. |
Andreas Aakerberg; Kamal Nasrollahi; Thomas B. Moeslund; | arxiv-cs.CV | 2021-02-05 |
| 445 | Robust Single-step Adversarial Training with Regularizer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a novel Fast Gradient Sign Method with PGD Regularization (FGSMPR) to boost the efficiency of adversarial training without catastrophic overfitting. |
Lehui Xie; Yaopeng Wang; Jia-Li Yin; Ximeng Liu; | arxiv-cs.LG | 2021-02-05 |
| 446 | Robust Pedestrian Detection in Thermal Imagery Using Synthesized Images Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We apply our generative data augmentation strategy in order to adapt a pretrained YOLOv3 pedestrian detector to detection in the thermal-only domain. |
MY KIEU et. al. | arxiv-cs.CV | 2021-02-03 |
| 447 | Digital Twins Based on Bidirectional LSTM and GAN for Modelling The COVID-19 Pandemic Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we introduce two digital twins of a SEIRS model applied to an idealised town. |
CÉSAR QUILODRÁN-CASAS et. al. | arxiv-cs.LG | 2021-02-03 |
| 448 | IWA: Integrated Gradient Based White-box Attacks for Fooling Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on these three works, we propose two Integrated gradient based White-box Adversarial example generation algorithms (IWA): IFPA and IUA. |
Yixiang Wang; Jiqiang Liu; Xiaolin Chang; Jelena Mišić; Vojislav B. Mišić; | arxiv-cs.LG | 2021-02-03 |
| 449 | Learning Diverse-Structured Networks for Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we argue that NA and AT cannot be handled independently, since given a dataset, the optimal NA in ST would be no longer optimal in AT. |
XUEFENG DU et. al. | arxiv-cs.LG | 2021-02-03 |
| 450 | Organization of A Latent Space Structure in VAE/GAN Trained By Navigation Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel artificial cognitive mapping system using generative deep neural networks (VAE/GAN), which can map input images to latent vectors and generate temporal sequences internally. |
Hiroki Kojima; Takashi Ikegami; | arxiv-cs.LG | 2021-02-02 |
| 451 | Distributed Conditional Generative Adversarial Networks (GANs) for Data-Driven Millimeter Wave Communications in UAV Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a novel framework is proposed to perform data-driven air-to-ground (A2G) channel estimation for millimeter wave (mmWave) communications in an unmanned aerial vehicle (UAV) wireless network. |
Qianqian Zhang; Aidin Ferdowsi; Walid Saad; Mehdi Bennis; | arxiv-cs.IT | 2021-02-02 |
| 452 | On Robustness of Neural Semantic Parsers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide the empirical study on the robustness of semantic parsers in the presence of adversarial attacks. |
Shuo Huang; Zhuang Li; Lizhen Qu; Lei Pan; | arxiv-cs.CL | 2021-02-02 |
| 453 | Toon2real: Translating Cartoon Images to Realistic Images IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim to translate cartoon images to photo-realistic images using GAN. |
K. M. Arefeen Sultan; Mohammad Imrul Jubair; MD. Nahidul Islam; Sayed Hossain Khan; | arxiv-cs.CV | 2021-02-01 |
| 454 | Enjoy Your Editing: Controllable GANs for Image Editing Via Latent Space Navigation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose quantitative evaluation strategies for measuring controllable editing performance, unlike prior work, which primarily focuses on qualitative evaluation. |
Peiye Zhuang; Oluwasanmi Koyejo; Alexander G. Schwing; | arxiv-cs.CV | 2021-02-01 |
| 455 | Robust Adversarial Attacks Against DNN-Based Wireless Communication Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an input-agnostic, undetectable, and robust adversarial attack against DNN-based wireless communication systems in both white-box and black-box scenarios. |
Alireza Bahramali; Milad Nasr; Amir Houmansadr; Dennis Goeckel; Don Towsley; | arxiv-cs.CR | 2021-02-01 |
| 456 | System-reliability Based Multi-ensemble of GAN and One-class Joint Gaussian Distributions for Unsupervised Real-time Structural Health Monitoring Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study introduces an unsupervised real-time SHM method with a mixture of low- and high-dimensional features without a case-dependent extraction scheme. |
Mohammad Hesam Soleimani-Babakamali; Reza Sepasdar; Kourosh Nasrollahzadeh; Rodrigo Sarlo; | arxiv-cs.LG | 2021-02-01 |
| 457 | ConvNets for Counting: Object Detection of Transient Phenomena in Steelpan Drums Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We train an object detector built from convolutional neural networks to count interference fringes in elliptical antinode regions visible in frames of high-speed video recordings of transient oscillations in Caribbean steelpan drums illuminated by electronic speckle pattern interferometry (ESPI). |
Scott H. Hawley; Andrew C. Morrison; | arxiv-cs.CV | 2021-01-31 |
| 458 | RoutingGAN: Routing Age Progression and Regression with Disentangled Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these deficiencies and have the best of both worlds, this paper introduces a dropout-like method based on GAN~(RoutingGAN) to route different effects in a high-level semantic feature space. |
Zhizhong Huang; Junping Zhang; Hongming Shan; | arxiv-cs.CV | 2021-01-31 |
| 459 | Demonstrating The Evolution of GANs Through T-SNE Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose an evaluation method based on t-distributed Stochastic Neighbour Embedding (t-SNE) to assess the progress of GANs and visualize the distribution learned by generators in training. |
Victor Costa; Nuno Lourenço; João Correia; Penousal Machado; | arxiv-cs.NE | 2021-01-31 |
| 460 | Mixup Regularized Adversarial Networks for Multi-Domain Text Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a mixup regularized adversarial network (MRAN) to address these two issues. |
Yuan Wu; Diana Inkpen; Ahmed El-Roby; | arxiv-cs.CL | 2021-01-31 |
| 461 | Admix: Enhancing The Transferability of Adversarial Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a new input transformation based attack method called Admix that considers the input image and a set of images randomly sampled from other categories. |
Xiaosen Wang; Xuanran He; Jingdong Wang; Kun He; | arxiv-cs.CV | 2021-01-31 |
| 462 | Time Series (re)sampling Using Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel bootstrap procedure for dependent data based on Generative Adversarial networks (GANs). |
Christian M. Dahl; Emil N. Sørensen; | arxiv-cs.LG | 2021-01-30 |
| 463 | Resolution Enhancement in The Recovery of Underdrawings Via Style Transfer By Generative Adversarial Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We apply generative adversarial convolutional neural networks to the problem of style transfer to underdrawings and ghost-images in x-rays of fine art paintings with a special focus on enhancing their spatial resolution. |
George Cann; Anthony Bourached; Ryan-Rhys Griffiths; David Stork; | arxiv-cs.CV | 2021-01-30 |
| 464 | Using Multiple Generative Adversarial Networks to Build Better-Connected Levels for Mega Man Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper focuses on combining GAN-generated segments in a snaking pattern to create levels for Mega Man. |
Benjamin Capps; Jacob Schrum; | arxiv-cs.NE | 2021-01-30 |
| 465 | Cortical Features for Defense Against Adversarial Audio Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose using a computational model of the auditory cortex as a defense against adversarial attacks on audio. |
Ilya Kavalerov; Frank Zheng; Wojciech Czaja; Rama Chellappa; | arxiv-cs.SD | 2021-01-30 |
| 466 | An Adaptive Artificial Neural Network-based Generative Design Method for Layout Designs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, an adaptive artificial neural network-based generative design approach is proposed and developed. |
Chao Qian; Renkai Tan; Wenjing Ye; | arxiv-cs.LG | 2021-01-29 |
| 467 | Topological Interference Management with Adversarial Perturbation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider the topological interference management (TIM) problem in a dynamic setting, where an adversary perturbs network topology to prevent the exploitation of sophisticated coding opportunities (e.g., interference alignment). |
Ya-Chun Liang; Chung-Shou Liao; Xinping Yi; | arxiv-cs.IT | 2021-01-29 |
| 468 | Reconstructing Perceptive Images from Brain Activity By Shape-Semantic GAN IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the theory that visual features are hierarchically represented in cortex, we propose to break the complex visual signals into multi-level components and decode each component separately. |
Tao Fang; Yu Qi; Gang Pan; | arxiv-cs.NE | 2021-01-28 |
| 469 | The Hidden Tasks of Generative Adversarial Networks: An Alternative Perspective on GAN Training Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an alternative perspective on the training of generative adversarial networks (GANs), showing that the training step for a GAN generator decomposes into two implicit sub-problems. |
Romann M. Weber; | arxiv-cs.LG | 2021-01-28 |
| 470 | Adversarial Attacks on Deep Learning Based Power Allocation in A Massive MIMO Network Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we extend this to regression problems and show that adversarial attacks can break DL-based power allocation in the downlink of a massive multiple-input-multiple-output (maMIMO) network. |
B. R. Manoj; Meysam Sadeghi; Erik G. Larsson; | arxiv-cs.IT | 2021-01-28 |
| 471 | Increasing The Confidence of Deep Neural Networks By Coverage Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a lightweight monitoring architecture based on coverage paradigms to enhance the model robustness against different unsafe inputs. |
Giulio Rossolini; Alessandro Biondi; Giorgio Carlo Buttazzo; | arxiv-cs.LG | 2021-01-28 |
| 472 | Detecting Malicious Accounts Showing Adversarial Behavior in Permissionless Blockchains Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these problems, we aim at automatically flagging blockchain accounts that originate such malicious exploitation of accounts of other participants. |
Rachit Agarwal; Tanmay Thapliyal; Sandeep K. Shukla; | arxiv-cs.CR | 2021-01-28 |
| 473 | Adversarial Learning with Cost-Sensitive Classes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a framework combining cost-sensitive classification and adversarial learning together to train a model that can distinguish between protected and unprotected classes, such that the protected classes are less vulnerable to adversarial examples. |
Haojing Shen; Sihong Chen; Ran Wang; Xizhao Wang; | arxiv-cs.LG | 2021-01-28 |
| 474 | Generative Multi-Label Zero-Shot Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce different fusion approaches at the attribute-level, feature-level and cross-level (across attribute and feature-levels) for synthesizing multi-label features from their corresponding multi-label class embedding. |
AKSHITA GUPTA et. al. | arxiv-cs.CV | 2021-01-27 |
| 475 | Adversarial Active Learning Based Heterogeneous Graph Neural Network for Fake News Detection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we attempt to solve the fake news detection problem with the support of a news-oriented HIN. |
Yuxiang Ren; Bo Wang; Jiawei Zhang; Yi Chang; | arxiv-cs.SI | 2021-01-27 |
| 476 | Detecting Adversarial Examples By Input Transformations, Defense Perturbations, and Voting IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper extensively explores the detection of adversarial examples via image transformations and proposes a novel methodology, called \textit{defense perturbation}, to detect robust adversarial examples with the same input transformations the adversarial examples are robust to. |
Federico Nesti; Alessandro Biondi; Giorgio Buttazzo; | arxiv-cs.CV | 2021-01-27 |
| 477 | Improving Neural Network Robustness Through Neighborhood Preserving Layers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new neighborhood preserving layer which can replace these fully connected layers to improve the network robustness. |
Bingyuan Liu; Christopher Malon; Lingzhou Xue; Erik Kruus; | arxiv-cs.LG | 2021-01-27 |
| 478 | Differentiable Sampling of Molecular Geometries with Uncertainty-based Adversarial Attacks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we exploit automatic differentiation to drive atomistic systems towards high-likelihood, high-uncertainty configurations without the need for molecular dynamics simulations. |
Daniel Schwalbe-Koda; Aik Rui Tan; Rafael Gómez-Bombarelli; | arxiv-cs.LG | 2021-01-27 |
| 479 | Evolutionary Generative Adversarial Networks with Crossover Based Knowledge Distillation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: And we combine the crossover operator with evolutionary generative adversarial networks (EGAN) to implement the evolutionary generative adversarial networks with crossover (CE-GAN). |
Junjie Li; Junwei Zhang; Xiaoyu Gong; Shuai Lü; | arxiv-cs.LG | 2021-01-26 |
| 480 | Investigating The Significance of Adversarial Attacks and Their Relation to Interpretability for Radar-based Human Activity Recognition Systems IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the vulnerability of radar-based CNNs to adversarial attacks, and where these radar-based CNNs have been designed to recognize human gestures. |
UTKU OZBULAK et. al. | arxiv-cs.CV | 2021-01-26 |
| 481 | Towards Universal Physical Attacks On Cascaded Camera-Lidar 3D Object Detection Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a universal and physically realizable adversarial attack on a cascaded multi-modal deep learning network (DNN), in the context of self-driving cars. |
Mazen Abdelfattah; Kaiwen Yuan; Z. Jane Wang; Rabab Ward; | arxiv-cs.CV | 2021-01-26 |
| 482 | The Effect of Class Definitions on The Transferability of Adversarial Attacks Against Forensic CNNs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we demonstrate that adversarial attacks on forensic CNNs are even less transferrable than previously thought even between virtually identical CNN architectures! |
Xinwei Zhao; Matthew C. Stamm; | arxiv-cs.CV | 2021-01-26 |
| 483 | Adversarial Text-to-Image Synthesis: A Review IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this review, we contextualize the state of the art of adversarial text-to-image synthesis models, their development since their inception five years ago, and propose a taxonomy based on the level of supervision. |
Stanislav Frolov; Tobias Hinz; Federico Raue; Jörn Hees; Andreas Dengel; | arxiv-cs.CV | 2021-01-25 |
| 484 | GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To assist designers, we develop a model GUIGAN to automatically generate GUI designs. |
Tianming Zhao; Chunyang Chen; Yuanning Liu; Xiaodong Zhu; | arxiv-cs.HC | 2021-01-25 |
| 485 | Self Sparse Generative Adversarial Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a Self Sparse Generative Adversarial Network (Self-Sparse GAN) that reduces the parameter space and alleviates the zero gradient problem. |
Wenliang Qian; Yang Xu; Wangmeng Zuo; Hui Li; | arxiv-cs.CV | 2021-01-25 |
| 486 | A General Framework Combining Generative Adversarial Networks and Mixture Density Networks for Inverse Modeling in Microstructural Materials Design IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a framework consisting of generative adversarial networks and mixture density networks for inverse modeling, and it is evaluated on a materials science dataset for microstructural materials design. |
ZIJIANG YANG et. al. | arxiv-cs.LG | 2021-01-25 |
| 487 | Generalizing Adversarial Examples By AdaBelief Optimizer IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this issue, we propose an AdaBelief iterative Fast Gradient Sign Method (AB-FGSM) to generalize adversarial examples. |
Yixiang Wang; Jiqiang Liu; Xiaolin Chang; | arxiv-cs.LG | 2021-01-25 |
| 488 | Probabilistic Robustness Analysis for DNNs Based on PAC Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a black box based approach for analysing deep neural networks (DNNs). |
Renjue Li; Pengfei Yang; Cheng-Chao Huang; Bai Xue; Lijun Zhang; | arxiv-cs.LG | 2021-01-25 |
| 489 | CGANs for Cartoon to Real-life Images IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This project aims to evaluate the robustness of the Pix2Pix model by applying the Pix2Pix model to datasets consisting of cartoonized images. |
Pranjal Singh Rajput; Kanya Satis; Sonnya Dellarosa; Wenxuan Huang; Obinna Agba; | arxiv-cs.CV | 2021-01-24 |
| 490 | Fighting Deepfakes By Detecting GAN DCT Anomalies IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a new fast detection method able to discriminate Deepfake images with high precision is proposed. |
Oliver Giudice; Luca Guarnera; Sebastiano Battiato; | arxiv-cs.CV | 2021-01-24 |
| 491 | A Joint Representation Learning and Feature Modeling Approach for One-class Recognition IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we argue that both of these approaches have their own limitations; and a more effective solution can be obtained by combining the two. |
Pramuditha Perera; Vishal Patel; | arxiv-cs.CV | 2021-01-24 |
| 492 | Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularization IF:2 Related Papers Related Patents Related Grants Related Orgs |