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
| Title | Author(s) | Highlight | Category | Date | |
|---|---|---|---|---|---|
| 1 | Pixel-based Facial Expression Synthesis | ARBISH AKRAM et. al. | In this work, we propose a pixel-based facial expression synthesis method in which each output pixel observes only one input pixel. | CS.arxiv | 2020-10-27 |
| 2 | $γ$-Models: Generative Temporal Difference Learning For Infinite-Horizon Prediction | MICHAEL JANNER et. al. | We introduce the $\gamma$-model, a predictive model of environment dynamics with an infinite probabilistic horizon. | CS.arxiv | 2020-10-27 |
| 3 | Anti-perturbation Of Online Social Networks By Graph Label Transition | JUN ZHUANG et. al. | To address these issues, we propose a novel graph label transition model, named GraphLT, to improve the robustness of the OSN classifier by transiting the node latent representation based on dynamic conditional label transition. | CS.arxiv | 2020-10-27 |
| 4 | Fast Local Attack: Generating Local Adversarial Examples For Object Detectors | QUANYU LIAO et. al. | Most existing research focuses on attacking image classifiers or anchor-based object detectors, but they generate globally perturbation on the whole image, which is unnecessary. | CS.arxiv | 2020-10-27 |
| 5 | A Distributed Training Algorithm Of Generative Adversarial Networks With Quantized Gradients | XIAOJUN CHEN et. al. | In this paper, we propose a {distributed GANs training algorithm with quantized gradient, dubbed DQGAN,} which is the first distributed training method with quantized gradient for GANs. | CS.arxiv | 2020-10-26 |
| 6 | Restrained Generative Adversarial Network Against Overfitting In Numeric Data Augmentation | WEI WANG et. al. | By analyzing the Directed Graphical Model (DGM), we propose a theoretical restraint, independence on the loss function, to suppress the overfitting. | CS.arxiv | 2020-10-26 |
| 7 | LEAD: Least-Action Dynamics For Min-Max Optimization | REYHANE ASKARI HEMMAT et. al. | In this work, we take a novel approach to address this issue by casting min-max optimization as a physical system. | CS.arxiv | 2020-10-26 |
| 8 | Robustness May Be At Odds With Fairness: An Empirical Study On Class-wise Accuracy | PHILIPP BENZ et. al. | In this preregistration submission, we propose an empirical study on the class-wise accuracy and robustness of adversarially trained models. | CS.arxiv | 2020-10-26 |
| 9 | An Adversarial Domain Separation Framework For Septic Shock Early Prediction Across EHR Systems | FARZANEH KHOSHNEVISAN et. al. | In this work, we propose a general domain adaptation (DA) framework that tackles two categories of discrepancies in EHRs collected from different medical systems: one is caused by heterogeneous patient populations (covariate shift) and the other is caused by variations in data collection procedures (systematic bias). | CS.arxiv | 2020-10-26 |
| 10 | Decentralized Attribution Of Generative Models | CHANGHOON KIM et. al. | Our major contributions are the derivation of the sufficient conditions for decentralized attribution and the design of keys following these conditions. | CS.arxiv | 2020-10-26 |
| 11 | GreedyFool: Distortion-Aware Sparse Adversarial Attack | XIAOYI DONG et. al. | In this paper, we propose a novel two-stage distortion-aware greedy-based method dubbed as “GreedyFool. | CS.arxiv | 2020-10-26 |
| 12 | Denial-of-Service Attacks On C-V2X Networks | NATAŠA TRKULJA et. al. | This work contributes a novel set of Denial-of-Service (DoS) attacks on C-V2X networks operating in Mode 4. | CS.arxiv | 2020-10-26 |
| 13 | Reducing The Computational Cost Of Deep Generative Models With Binary Neural Networks | THOMAS BIRD et. al. | In this work we show, for the first time, that we can successfully train generative models which utilize binary neural networks. | CS.arxiv | 2020-10-26 |
| 14 | IR-GAN: Room Impulse Response Generator For Speech Augmentation | ANTON RATNARAJAH et. al. | We present a Generative Adversarial Network (GAN) based room impulse response generator for generating realistic synthetic room impulse responses. | CS.arxiv | 2020-10-25 |
| 15 | Dynamic Adversarial Patch For Evading Object Detection Models | SHAHAR HOORY et. al. | In this study, we present an innovative attack method against object detectors applied in a real-world setup that addresses some of the limitations of existing attacks. | CS.arxiv | 2020-10-25 |
| 16 | Discriminative Feature Generation For Classification Of Imbalanced Data | SUNGHO SUH et. al. | In this paper, we propose a novel supervised discriminative feature generation (DFG) method for a minority class dataset. | CS.arxiv | 2020-10-24 |
| 17 | Graph Information Bottleneck | TAILIN WU et. al. | Here we introduce Graph Information Bottleneck (GIB), an information-theoretic principle that optimally balances expressiveness and robustness of the learned representation of graph-structured data. | CS.arxiv | 2020-10-24 |
| 18 | Train Simultaneously, Generalize Better: Stability Of Gradient-based Minimax Learners | FARZAN FARNIA et. al. | In this paper, we show that the optimization algorithm also plays a key role in the generalization performance of the trained minimax model. | CS.arxiv | 2020-10-23 |
| 19 | S2cGAN: Semi-Supervised Training Of Conditional GANs With Fewer Labels | ARUNAVA CHAKRABORTY et. al. | We propose a framework for semi-supervised training of cGANs which utilizes sparse labels to learn the conditional mapping, and at the same time leverages a large amount of unsupervised data to learn the unconditional distribution. | CS.arxiv | 2020-10-23 |
| 20 | Learn Robust Features Via Orthogonal Multi-Path | KUN FANG et. al. | To defend adversarial attacks, we design a block containing multiple paths to learn robust features and the parameters of these paths are required to be orthogonal with each other. | CS.arxiv | 2020-10-23 |
| 21 | Novel View Synthesis From Only A 6-DoF Camera Pose By Two-stage Networks | XIANG GUO et. al. | Different from the existing works, which need the reference images or 3D models of the scene to generate images under novel views, we propose a novel paradigm to this problem. | CS.arxiv | 2020-10-22 |
| 22 | Few-Shot Adaptation Of Generative Adversarial Networks | ESTHER ROBB et. al. | This paper proposes a simple and effective method, Few-Shot GAN (FSGAN), for adapting GANs in few-shot settings (less than 100 images). | CS.arxiv | 2020-10-22 |
| 23 | Error Bounds Of Imitating Policies And Environments | TIAN XU et. al. | Noticed that by considering the environment transition model as a dual agent, imitation learning can also be used to learn the environment model. | CS.arxiv | 2020-10-22 |
| 24 | Lightweight Generative Adversarial Networks For Text-Guided Image Manipulation | BOWEN LI et. al. | We propose a novel lightweight generative adversarial network for efficient image manipulation using natural language descriptions. | CS.arxiv | 2020-10-22 |
| 25 | TLGAN: Document Text Localization Using Generative Adversarial Nets | DONGYOUNG KIM et. al. | Here we present document Text Localization Generative Adversarial Nets (TLGAN) which are deep neural networks to perform the text localization from digital image. | CS.arxiv | 2020-10-22 |
| 26 | Quantitative Analysis Of Robot Gesticulation Behavior | UNAI ZABALA et. al. | In this paper a quantitative analysis is performed that compares two Generative Adversarial Networks based gesture generation approaches. | CS.arxiv | 2020-10-22 |
| 27 | CycleGAN-VC3: Examining And Improving CycleGAN-VCs For Mel-spectrogram Conversion | TAKUHIRO KANEKO et. al. | To remedy this, we propose CycleGAN-VC3, an improvement of CycleGAN-VC2 that incorporates time-frequency adaptive normalization (TFAN). | CS.arxiv | 2020-10-22 |
| 28 | Defense-guided Transferable Adversarial Attacks | ZIFEI ZHANG et. al. | Under the query-free black-box scenario, adversarial examples are hard to transfer to unknown models, and several methods have been proposed with low transferability. | CS.arxiv | 2020-10-22 |
| 29 | Once-for-All Adversarial Training: In-Situ Tradeoff Between Robustness And Accuracy For Free | HAOTAO WANG et. al. | Our proposed framework, Once-for-all Adversarial Training (OAT), is built on an innovative model-conditional training framework, with a controlling hyper-parameter as the input. | CS.arxiv | 2020-10-22 |
| 30 | Enabling Certification Of Verification-agnostic Networks Via Memory-efficient Semidefinite Programming | SUMANTH DATHATHRI et. al. | In this work, we propose a first-order dual SDP algorithm that (1) requires memory only linear in the total number of network activations, (2) only requires a fixed number of forward/backward passes through the network per iteration. | CS.arxiv | 2020-10-22 |
| 31 | One Model To Reconstruct Them All: A Novel Way To Use The Stochastic Noise In StyleGAN | CHRISTIAN BARTZ et. al. | We present a novel StyleGAN-based autoencoder architecture, which can reconstruct images with very high quality across several data domains. | CS.arxiv | 2020-10-21 |
| 32 | Class-Conditional Defense GAN Against End-to-End Speech Attacks | MOHAMMAD ESMAEILPOUR et. al. | In this paper we propose a novel defense approach against end-to-end adversarial attacks developed to fool advanced speech-to-text systems such as DeepSpeech and Lingvo. | CS.arxiv | 2020-10-21 |
| 33 | DPD-InfoGAN: Differentially Private Distributed InfoGAN | VAIKKUNTH MUGUNTHAN et. al. | To address this problem, we propose a differentially private version of InfoGAN (DP-InfoGAN). | CS.arxiv | 2020-10-21 |
| 34 | A Distributional Robustness Certificate By Randomized Smoothing | JUNGANG YANG et. al. | We focus on certified robustness of smoothed classifiers in this work, and propose to use the worst-case population loss over noisy inputs as a robustness metric. | CS.arxiv | 2020-10-21 |
| 35 | Two-Stage Generative Adversarial Networks For Document Image Binarization With Color Noise And Background Removal | SUNGHO SUH et. al. | In this paper, we propose a two-stage color document image enhancement and binarization method using generative adversarial neural networks. | CS.arxiv | 2020-10-20 |
| 36 | Boosting Gradient For White-Box Adversarial Attacks | HONGYING LIU et. al. | In contrast, in this paper, we focus on the properties of the widely-used ReLU activation function, and discover that there exist two phenomena (i.e., wrong blocking and over transmission) misleading the calculation of gradients in ReLU during the backpropagation. | CS.arxiv | 2020-10-20 |
| 37 | Robust Neural Networks Inspired By Strong Stability Preserving Runge-Kutta Methods | BYUNGJOO KIM et. al. | Motivated by the SSP property and a generalized Runge-Kutta method, we propose Strong Stability Preserving networks (SSP networks) which improve robustness against adversarial attacks. | CS.arxiv | 2020-10-20 |
| 38 | VENOMAVE: Clean-Label Poisoning Against Speech Recognition | HOJJAT AGHAKHANI et. al. | In this paper, we present the first data poisoning attack in the audio domain, called VENOMAVE. | CS.arxiv | 2020-10-20 |
| 39 | Towards Understanding The Dynamics Of The First-Order Adversaries | ZHUN DENG et. al. | In this paper, we analyze the dynamics of the maximization step towards understanding the experimentally observed effectiveness of this defense mechanism. | CS.arxiv | 2020-10-20 |
| 40 | SCOP: Scientific Control For Reliable Neural Network Pruning | YEHUI TANG et. al. | This paper proposes a reliable neural network pruning algorithm by setting up a scientific control. | CS.arxiv | 2020-10-20 |
| 41 | Multi-Modal Super Resolution For Dense Microscopic Particle Size Estimation | SARVESH PATIL et. al. | We propose a powerful application of a combination of two Conditional Generative Adversarial Networks (cGANs) that Super Resolve OM images to look like Scanning Electron Microscope (SEM) images. | CS.arxiv | 2020-10-19 |
| 42 | A GAN-based Framework For Modeling Hashtag Popularity Dynamics Using Assistive Information | AVIRUP SAHA et. al. | In this paper, we propose a marked TPP based on Generative Adversarial Networks (GANs) which can seamlessly incorporate the assistive information necessary to capture the above effects and successfully forecast distant popularity trends. | CS.cikm | 2020-10-19 |
| 43 | Attacking Recommender Systems With Augmented User Profiles | CHEN LIN et. al. | In this paper, we study the shilling attack: a subsistent and profitable attack where an adversarial party injects a number of user profiles to promote or demote a target item. | CS.cikm | 2020-10-19 |
| 44 | Exploring Missing Interactions: A Convolutional Generative Adversarial Network For Collaborative Filtering | FENG YUAN et. al. | In this work, we focus on the semantic-rich user-item interactions in a recommender system and propose a novel generative adversarial network (GAN) named Convolutional Generative Collaborative Filtering (Conv-GCF). | CS.cikm | 2020-10-19 |
| 45 | Neural Formatting For Spreadsheet Tables | HAOYU DONG DONG et. al. | In this paper, we propose CellGAN, a neural formatting model for learning and recommending formats of spreadsheet tables. | CS.cikm | 2020-10-19 |
| 46 | GANs For Learning From Very High Class Conditional Noisy Labels | SANDHYA TRIPATHI et. al. | We use Generative Adversarial Networks (GANs) to design a class conditional label noise (CCN) robust scheme for binary classification. | CS.arxiv | 2020-10-19 |
| 47 | LT-GAN: Self-Supervised GAN With Latent Transformation Detection | PARTH PATEL et. al. | We propose a self-supervised approach (LT-GAN) to improve the generation quality and diversity of images by estimating the GAN-induced transformation (i.e. transformation induced in the generated images by perturbing the latent space of generator). | CS.arxiv | 2020-10-19 |
| 48 | A View-Adversarial Framework For Multi-View Network Embedding | DONGQI FU et. al. | In this paper, we propose a view-adversarial framework to generate comprehensive and robust multi-view network representations named VANE, which is based on two adversarial games. | CS.cikm | 2020-10-19 |
| 49 | Learning Formatting Style Transfer And Structure Extraction For Spreadsheet Tables With A Hybrid Neural Network Architecture | HAOYU DONG et. al. | In this paper, we propose techniques for table formatting style transfer, i.e., to automatically format a target table according to the style of a reference table. | CS.cikm | 2020-10-19 |
| 50 | LB-CGM: Latent Based Conditional Generative Model With Reliable Distribution Prediction | YICHEN YAO et. al. | In this paper, we combine the advantages of both GANs (Generative Adversarial Nets) and VAEs (Variational Auto-Encoders), and introduce a latent-based conditional generative model (LB-CGM) to handle the distribution regression problems. | CS.cikm | 2020-10-19 |
| 51 | Generative Adversarial Attributed Network Anomaly Detection | ZHENXING CHEN et. al. | In this paper, we propose a generative adversarial attributed network (GAAN) anomaly detection framework. | CS.cikm | 2020-10-19 |
| 52 | GeneraLight: Improving Environment Generalization Of Traffic Signal Control Via Meta Reinforcement Learning | HUICHU ZHANG et. al. | In this paper, we design a novel traffic flow generator based on Wasserstein generative adversarial network to generate sufficient diverse and quality traffic flows and use them to build proper training and testing environments. | CS.cikm | 2020-10-19 |
| 53 | FLAG: Adversarial Data Augmentation For Graph Neural Networks | KEZHI KONG et. al. | We propose a simple but effective solution, FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training, and boosts performance at test time. | CS.arxiv | 2020-10-19 |
| 54 | SWE2: SubWord Enriched And Significant Word Emphasized Framework For Hate Speech Detection | GUANYI MOU et. al. | In this paper, we address the hate speech problem and propose a novel hate speech detection framework called SWE2, which only relies on the content of messages and automatically identifies hate speech. | CS.cikm | 2020-10-19 |
| 55 | Verifying The Causes Of Adversarial Examples | HONGLIN LI et. al. | In this paper, we present a collection of potential causes of adversarial examples and verify (or partially verify) them through carefully-designed controlled experiments. | CS.arxiv | 2020-10-19 |
| 56 | Optimism In The Face Of Adversity: Understanding And Improving Deep Learning Through Adversarial Robustness | GUILLERMO ORTIZ-JIMENEZ et. al. | But, in contrast to the mainstream pessimistic perspective of adversarial robustness, we focus on the main positive aspects that it entails. | CS.arxiv | 2020-10-19 |
| 57 | Multi-task Adversarial Spatial-Temporal Networks For Crowd Flow Prediction | SENZHANG WANG et. al. | In this paper, we study the novel problem of predicting the crowd flow and flow OD simultaneously, and propose a multi-task adversarial spatial-temporal network model entitled MT-ASTN to effectively address it. | CS.cikm | 2020-10-19 |
| 58 | Continual Unsupervised Domain Adaptation With Adversarial Learning | JOONHYUK KIM et. al. | To deal with the problem above, we propose Continual Unsupervised Domain Adaptation with Adversarial learning (CUDA^2) framework, which can generally be applicable to other UDA methods conducting adversarial learning. | CS.arxiv | 2020-10-19 |
| 59 | Helix: DGA Domain Embeddings For Tracking And Exploring Botnets | LIOR SIDI et. al. | In this paper, we present Helix, a method for tracking and exploring botnets. | CS.cikm | 2020-10-19 |
| 60 | Seed-free Graph De-anonymiztiation With Adversarial Learning | KAIYANG LI et. al. | In this paper, a seed-free graph de-anonymization method is proposed, where a deep neural network is adopted to learn features and an adversarial framework is employed for node matching. | CS.cikm | 2020-10-19 |
| 61 | UPON: User Profile Transferring Across Networks | MENGTING DIAO et. al. | Motivated by such observations, in this paper, we for the first time propose to study the user profiling problem from the transfer learning perspective. | CS.cikm | 2020-10-19 |
| 62 | DATSING: Data Augmented Time Series Forecasting With Adversarial Domain Adaptation | HAILIN HU et. al. | In this work, we have developed, DATSING, a transfer learning-based framework that effectively leverages cross-domain time series latent representations to augment target domain forecasting. | CS.cikm | 2020-10-19 |
| 63 | Self-Attention Generative Adversarial Network For Speech Enhancement | HUY PHAN et. al. | To remedy this issue, we propose a self-attention layer adapted from non-local attention, coupled with the convolutional and deconvolutional layers of a speech enhancement GAN (SEGAN) using raw signal input. | CS.arxiv | 2020-10-18 |
| 64 | Image GANs Meet Differentiable Rendering For Inverse Graphics And Interpretable 3D Neural Rendering | YUXUAN ZHANG et. al. | In this paper, we aim to extract and disentangle 3D knowledge learned by generative models by utilizing differentiable renderers. | CS.arxiv | 2020-10-18 |
| 65 | FADER: Fast Adversarial Example Rejection | FRANCESCO CRECCHI et. al. | The first main contribution of this work is the review of these detection methods in the form of a unifying framework designed to accommodate both existing defenses and newer ones to come. | CS.arxiv | 2020-10-18 |
| 66 | DE-GAN: A Conditional Generative Adversarial Network For Document Enhancement | MOHAMED ALI SOUIBGUI et. al. | In this paper, we propose an effective end-to-end framework named Document Enhancement Generative Adversarial Networks (DE-GAN) that uses the conditional GANs (cGANs) to restore severely degraded document images. | CS.arxiv | 2020-10-17 |
| 67 | Finding Physical Adversarial Examples For Autonomous Driving With Fast And Differentiable Image Compositing | JINGHAN YANG et. al. | We propose a scalable and efficient approach for finding adversarial physical modifications, using a differentiable approximation for the mapping from environmental modifications-namely, rectangles drawn on the road-to the corresponding video inputs to the controller network. | CS.arxiv | 2020-10-17 |
| 68 | A Generative Model Based Adversarial Security Of Deep Learning And Linear Classifier Models | ERHAT OZGUR CATAK et. al. | In this paper, we have proposed a mitigation method for adversarial attacks against machine learning models with an autoencoder model that is one of the generative ones. | CS.arxiv | 2020-10-17 |
| 69 | A Stochastic Neural Network For Attack-Agnostic Adversarial Robustness | PANAGIOTIS EUSTRATIADIS et. al. | We propose a new SNN that achieves state-of-the-art performance without relying on adversarial training, and enjoys solid theoretical justification. | CS.arxiv | 2020-10-17 |
| 70 | A Self-supervised Cascaded Refinement Network For Point Cloud Completion | XIAOGANG WANG et. al. | In view of these, we propose a self-supervised object completion method, which optimizes the training procedure solely on the partial input without utilizing the fully-complete ground truth. | CS.arxiv | 2020-10-17 |
| 71 | Multi-Adversarial Learning For Cross-Lingual Word Embeddings | HAOZHOU WANG et. al. | We assume instead that, especially across distant languages, the mapping is only piece-wise linear, and propose a multi-adversarial learning method. | CS.arxiv | 2020-10-16 |
| 72 | Learning Robust Algorithms For Online Allocation Problems Using Adversarial Training | GORAN ZUZIC et. al. | In this paper, we focus on the AdWords problem, which is a classical online budgeted matching problem of both theoretical and practical significance. | CS.arxiv | 2020-10-16 |
| 73 | Latent Vector Recovery Of Audio GANs | ANDREW KEYES et. al. | In this paper, we examine the task of recovering the latent vector of both synthesized and real audio. | CS.arxiv | 2020-10-16 |
| 74 | Collaborative Training Of GANs In Continuous And Discrete Spaces For Text Generation | YANGHOON KIM et. al. | In this paper, we propose a novel text GAN architecture that promotes the collaborative training of the continuous-space and discrete-space methods. | CS.arxiv | 2020-10-16 |
| 75 | On The Usage Of Generative Models For Network Anomaly Detection In Multivariate Time-Series | GASTÓN GARCÍA GONZÁLEZ et. al. | In this paper we introduce Net-GAN, a novel approach to network anomaly detection in time-series, using recurrent neural networks (RNNs) and generative adversarial networks (GAN). | CS.arxiv | 2020-10-16 |
| 76 | New Ideas And Trends In Deep Multimodal Content Understanding: A Review | WEI CHEN et. al. | Unlike classic reviews of deep learning where monomodal image classifiers such as VGG, ResNet and Inception module are central topics, this paper will examine recent multimodal deep models and structures, including auto-encoders, generative adversarial nets and their variants. | CS.arxiv | 2020-10-16 |
| 77 | Empty Cities: A Dynamic-Object-Invariant Space For Visual SLAM | BERTA BESCOS et. al. | In this paper we present a data-driven approach to obtain the static image of a scene, eliminating dynamic objects that might have been present at the time of traversing the scene with a camera. | CS.arxiv | 2020-10-15 |
| 78 | Non-saturating GAN Training As Divergence Minimization | MATT SHANNON et. al. | In this paper we show that non-saturating GAN training does in fact approximately minimize a particular f-divergence. | CS.arxiv | 2020-10-15 |
| 79 | Generalizing Universal Adversarial Attacks Beyond Additive Perturbations | YANGHAO ZHANG et. al. | More importantly, to unify both additive and non-additive perturbations, we propose a novel unified yet flexible framework for universal adversarial attacks, called GUAP, which is able to initiate attacks by additive perturbation, non-additive perturbation, or the combination of both. | CS.arxiv | 2020-10-15 |
| 80 | Maximum-Entropy Adversarial Data Augmentation For Improved Generalization And Robustness | LONG ZHAO et. al. | In this paper, we propose a novel and effective regularization term for adversarial data augmentation. | CS.arxiv | 2020-10-15 |
| 81 | A Hamiltonian Monte Carlo Method For Probabilistic Adversarial Attack And Learning | HONGJUN WANG et. al. | In this paper, we present an effective method, called Hamiltonian Monte Carlo with Accumulated Momentum (HMCAM), aiming to generate a sequence of adversarial examples. | CS.arxiv | 2020-10-15 |
| 82 | Deep Generative Modeling In Network Science With Applications To Public Policy Research | GAVIN S. HARTNETT et. al. | In this report, we formulate a research agenda of key methodological problems whose solutions would enable new advances across many areas of policy research. | CS.arxiv | 2020-10-15 |
| 83 | Garou: An Efficient And Secure Off-Blockchain Multi-Party Payment Hub | YONGJIE YE et. al. | In this paper, we propose Garou, a secure N-party payment hub that allows multiple parties to perform secure off-chain coin transfers. | CS.arxiv | 2020-10-15 |
| 84 | Semantic Segmentation For Partially Occluded Apple Trees Based On Deep Learning | ZIJUE CHEN et. al. | In this work, we apply two state-of-the-art supervised learning models U-Net and DeepLabv3, and a conditional Generative Adversarial Network Pix2Pix (with and without the discriminator) to segment partially occluded 2D-open-V apple trees. | CS.arxiv | 2020-10-14 |
| 85 | Learning Improvised Chatbots From Adversarial Modifications Of Natural Language Feedback | MAKESH NARSIMHAN SREEDHAR et. al. | In this work, we propose a generative adversarial model that converts noisy feedback into a plausible natural response in a conversation. | CS.arxiv | 2020-10-14 |
| 86 | AdaBelief Optimizer: Adapting Stepsizes By The Belief In Observed Gradients | JUNTANG ZHUANG et. al. | For many models such as convolutional neural networks (CNNs), adaptive methods typically converge faster but generalize worse compared to SGD; for complex settings such as generative adversarial networks (GANs), adaptive methods are typically the default because of their stability.We propose AdaBelief to simultaneously achieve three goals: fast convergence as in adaptive methods, good generalization as in SGD, and training stability. | CS.arxiv | 2020-10-14 |
| 87 | Human-guided Robot Behavior Learning: A GAN-assisted Preference-based Reinforcement Learning Approach | HUIXIN ZHAN et. al. | To reduce and minimize the need for human queries, we propose a new GAN-assisted human preference-based reinforcement learning approach that uses a generative adversarial network (GAN) to actively learn human preferences and then replace the role of human in assigning preferences. | CS.arxiv | 2020-10-14 |
| 88 | GreedyFool: An Imperceptible Black-box Adversarial Example Attack Against Neural Networks | HUI LIU et. al. | In this paper, we propose a novel black-box adversarial example attack named GreedyFool, which synthesizes adversarial examples based on the differential evolution and the greedy approximation. | CS.arxiv | 2020-10-14 |
| 89 | An Adversarial Attack Against Stacked Capsule Autoencoder | JIAZHU DAI et. al. | In this paper, we propose an evasion attack against SCAE. | CS.arxiv | 2020-10-14 |
| 90 | Viewmaker Networks: Learning Views For Unsupervised Representation Learning | ALEX TAMKIN et. al. | To address this, we propose viewmaker networks: generative models that learn to produce input-dependent views for contrastive learning. | CS.arxiv | 2020-10-14 |
| 91 | Video Game Level Repair Via Mixed Integer Linear Programming | HEJIA ZHANG et. al. | We propose a generate-then-repair framework for automatic generation of playable levels adhering to specific styles. | CS.arxiv | 2020-10-13 |
| 92 | F2GAN: Fusing-and-Filling GAN For Few-shot Image Generation | YAN HONG et. al. | In this paper, we propose a Fusing-and-Filling Generative Adversarial Network (F2GAN) to generate realistic and diverse images for a new category with only a few images. | CS.mm | 2020-10-12 |
| 93 | Robust Optimal Transport With Applications In Generative Modeling And Domain Adaptation | YOGESH BALAJI et. al. | In this paper, we resolve these issues by deriving a computationally-efficient dual form of the robust OT optimization that is amenable to modern deep learning applications. | CS.arxiv | 2020-10-12 |
| 94 | PCA-SRGAN: Incremental Orthogonal Projection Discrimination For Face Super-resolution | HAO DOU et. al. | To further improve the performance of GAN-based models on super-resolving face images, we propose PCA-SRGAN which pays attention to the cumulative discrimination in the orthogonal projection space spanned by PCA projection matrix of face data. | CS.mm | 2020-10-12 |
| 95 | Sequential Attention GAN For Interactive Image Editing | YU CHENG et. al. | To explore more practical and interactive real-life applications, we introduce a new task – Interactive Image Editing, where users can guide an agent to edit images via multi-turn textual commands on-the-fly. | CS.mm | 2020-10-12 |
| 96 | Amora: Black-box Adversarial Morphing Attack | RUN WANG et. al. | In this paper, we investigate and introduce a new type of adversarial attack to evade FR systems by manipulating facial content, called adversarial morphing attack (a.k.a. Amora). | CS.mm | 2020-10-12 |
| 97 | SketchMan: Learning To Create Professional Sketches | JIA LI et. al. | We propose a new challenging task sketch enhancement (SE) defined in an ill-posed space, i.e. enhancing a non-professional sketch (NPS) to a professional sketch (PS), which is a creative generation task different from sketch abstraction, sketch completion and sketch variation. | CS.mm | 2020-10-12 |
| 98 | HiFi-GAN: Generative Adversarial Networks For Efficient And High Fidelity Speech Synthesis | JUNGIL KONG et. al. | In this work, we propose HiFi-GAN, which achieves both efficient and high-fidelity speech synthesis. | CS.arxiv | 2020-10-12 |
| 99 | Omni-Directional Image Generation From Single Snapshot Image | KEISUKE OKUBO et. al. | For these purposes, a novel computer vision task to generate ODI from a single snapshot image is proposed in this paper. | CS.arxiv | 2020-10-12 |
| 100 | Unpaired Image Enhancement With Quality-Attention Generative Adversarial Network | ZHANGKAI NI et. al. | In this work, we aim to learn an unpaired image enhancement model, which can enrich low-quality images with the characteristics of high-quality images provided by users. | CS.mm | 2020-10-12 |
| 101 | Keep Running – AI Paintings Of Horse Figure And Portrait | JAMES SHE et. al. | Keep Running is a collection of human and machine generated paintings using a generative adversarial network technology. | CS.mm | 2020-10-12 |
| 102 | DeSmoothGAN: Recovering Details Of Smoothed Images Via Spatial Feature-wise Transformation And Full Attention | YIFEI HUANG et. al. | In this work, we propose DeSmoothGAN to utilize both characteristics specifically. | CS.mm | 2020-10-12 |
| 103 | Modeling Caricature Expressions By 3D Blendshape And Dynamic Texture | KEYU CHEN et. al. | This paper presents a solution to the problem, with an emphasis on enhancing the ability to create desired expressions and meanwhile preserve the identity exaggeration style of the caricature, which imposes challenges due to the complicated nature of caricatures. | CS.mm | 2020-10-12 |
| 104 | Talking Face Generation With Expression-Tailored Generative Adversarial Network | DAN ZENG et. al. | In this paper, we propose an end-to-end Expression-Tailored Generative Adversarial Network (ET-GAN) to generate an expression enriched talking face video of arbitrary identity. | CS.mm | 2020-10-12 |
| 105 | Revealing True Identity: Detecting Makeup Attacks In Face-based Biometric Systems | MOHAMMAD AMIN ARAB et. al. | In this paper, we propose a novel solution to address makeup attacks, which are the hardest to detect in such systems because makeup can substantially alter the facial features of a person, including making them appear older/younger by adding/hiding wrinkles, modifying the shape of eyebrows, beard, and moustache, and changing the color of lips and cheeks. | CS.mm | 2020-10-12 |
| 106 | Self-Paced Video Data Augmentation By Generative Adversarial Networks With Insufficient Samples | YUMENG ZHANG et. al. | In this study, we propose a generative data augmentation method for video classification using dynamic images. | CS.mm | 2020-10-12 |
| 107 | Increasing Video Perceptual Quality With GANs And Semantic Coding | LEONARDO GALTERI et. al. | In this work we show how such videos can be efficiently generated by shifting bitrate with masks derived via computer vision and how a deep generative adversarial network can be trained to restore video quality. | CS.mm | 2020-10-12 |
| 108 | JointFontGAN: Joint Geometry-Content GAN For Font Generation Via Few-Shot Learning | YANKUN XI et. al. | In this paper, we propose a novel model, JointFontGAN, to derive fonts, including both geometric structures and shape contents in correctness and consistency with very few font samples available. | CS.mm | 2020-10-12 |
| 109 | Lab2Pix: Label-Adaptive Generative Adversarial Network For Unsupervised Image Synthesis | LIANLI GAO et. al. | Therefore, we propose an unsupervised framework named Lab2Pix to adaptively synthesize images from labels by elegantly considering the particular properties of label to image synthesis task. | CS.mm | 2020-10-12 |
| 110 | GangSweep: Sweep Out Neural Backdoors By GAN | LIUWAN ZHU et. al. | This work proposes GangSweep, a new backdoor detection framework that leverages the super reconstructive power of Generative Adversarial Networks (GAN) to detect and ”sweep out” neural backdoors. | CS.mm | 2020-10-12 |
| 111 | Look Through Masks: Towards Masked Face Recognition With De-Occlusion Distillation | CHENYU LI et. al. | Inspired by recent progress on amodal perception, we propose to migrate the mechanism of amodal completion for the task of masked face recognition with an end-to-end de-occlusion distillation framework, which consists of two modules. | CS.mm | 2020-10-12 |
| 112 | Crossing You In Style: Cross-modal Style Transfer From Music To Visual Arts | CHENG-CHE LEE et. al. | Assuming that musical features can be properly mapped to visual contents through semantic links between the two domains, we solve the music-to-visual style transfer problem in two steps: music visualization and style transfer. | CS.mm | 2020-10-12 |
| 113 | Skin Textural Generation Via Blue-noise Gabor Filtering Based Generative Adversarial Network | HUI ZHANG et. al. | To this end, we propose a new facial noise generation method. | CS.mm | 2020-10-12 |
| 114 | Semantic Image Analogy With A Conditional Single-Image GAN | JIACHENG LI et. al. | To accomplish this task, we propose a novel method to model the patch-level correspondence between semantic layout and appearance of a single image by training a single-image GAN that takes semantic labels as conditional input. | CS.mm | 2020-10-12 |
| 115 | SpatialGAN: Progressive Image Generation Based On Spatial Recursive Adversarial Expansion | LEI ZHAO et. al. | In this paper, we propose a progressive spatial recursive adversarial expansion model(called SpatialGAN) capable of producing high-quality samples of the natural image. | CS.mm | 2020-10-12 |
| 116 | IR-GAN: Image Manipulation With Linguistic Instruction By Increment Reasoning | ZHENHUAN LIU et. al. | To address this issue, we propose an Increment Reasoning Generative Adversarial Network (IR-GAN), which aims to reason the consistency between visual increment in images and semantic increment in instructions. | CS.mm | 2020-10-12 |
| 117 | ChefGAN: Food Image Generation From Recipes | SIYUAN PAN et. al. | To achieve this, we propose a GANs based method termed ChefGAN. | CS.mm | 2020-10-12 |
| 118 | Dual Adversarial Network For Unsupervised Ground/Satellite-to-Aerial Scene Adaptation | JIANZHE LIN et. al. | Motivated by this, we propose a dual adversarial network for domain adaptation, where two adversarial learning processes are conducted iteratively, in correspondence with the feature adaptation and the classification task respectively. | CS.mm | 2020-10-12 |
| 119 | Neutral Face Game Character Auto-Creation Via PokerFace-GAN | TIANYANG SHI et. al. | In this paper, considering the above problems, we propose a novel method named "PokerFace-GAN" for neutral face game character auto-creation. | CS.mm | 2020-10-12 |
| 120 | Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective For Recognising Visual Patches | ZHI CHEN et. al. | To address these issues, we propose a novel framework called multi-patch generative adversarial nets (MPGAN) that synthesises local patch features and labels unseen classes with a novel weighted voting strategy. | CS.mm | 2020-10-12 |
| 121 | Generalized Zero-Shot Video Classification Via Generative Adversarial Networks | MINGYAO HONG et. al. | In order to solve this problem, we propose a description text dataset based on the UCF101 action recognition dataset. | CS.mm | 2020-10-12 |
| 122 | Learning Optimization-based Adversarial Perturbations For Attacking Sequential Recognition Models | XING XU et. al. | In this paper, we study the adversarial attack on the general and popular DNN structure of CNN+RNN, i.e., the combination of convolutional neural network (CNN) and recurrent neural network (RNN), which has been widely used in various SR tasks. | CS.mm | 2020-10-12 |
| 123 | Hearing Like Seeing: Improving Voice-Face Interactions And Associations Via Adversarial Deep Semantic Matching Network | KAI CHENG et. al. | In this paper, we present a novel adversarial deep semantic matching network for efficient voice-face interactions and associations, which can well learn the correspondence between voices and faces for various cross-modal matching and retrieval tasks. | CS.mm | 2020-10-12 |
| 124 | Deep Disturbance-Disentangled Learning For Facial Expression Recognition | DELIAN RUAN et. al. | In this paper, we propose a novel Deep Disturbance-disentangled Learning (DDL) method for FER. | CS.mm | 2020-10-12 |
| 125 | Adversarial Image Attacks Using Multi-Sample And Most-Likely Ensemble Methods | XIA DU et. al. | In this paper, we propose the multi-sample ensemble method (MSEM) and most-likely ensemble method (MLEM) to generate adversarial attacks that successfully fool the classifier for images in both the digital and real worlds. | CS.mm | 2020-10-12 |
| 126 | Finding Achilles’ Heel: Adversarial Attack On Multi-modal Action Recognition | DEEPAK KUMAR et. al. | Unfortunately, frame selection is usually computationally expensive in run-time, and adding noises to all frames is unrealistic, either. In this paper, we present a novel yet efficient approach to address this issue. | CS.mm | 2020-10-12 |
| 127 | Average Consensus: A Little Learning Goes A Long Way | BERNADETTE CHARRON-BOST et. al. | Inspired by the classic EqualNeighbor and Metropolis agreement rules for multi-agent systems, we design distributed algorithms for consensus and average consensus, which we show to operate in polynomial time in a synchronous temporal model. | CS.arxiv | 2020-10-12 |
| 128 | Joint Attribute Manipulation And Modality Alignment Learning For Composing Text And Image To Image Retrieval | FEIFEI ZHANG et. al. | In this paper, we devote to an emerging task in cross-modal retrieval, Composing Text and Image to Image Retrieval (CTI-IR), which aims at retrieving images relevant to a query image with text describing desired modifications to the query image. | CS.mm | 2020-10-12 |
| 129 | Adversarial Graph Representation Adaptation For Cross-Domain Facial Expression Recognition | YUAN XIE et. al. | In this work, we propose a novel Adversarial Graph Representation Adaptation (AGRA) framework that unifies graph representation propagation with adversarial learning for cross-domain holistic-local feature co-adaptation. | CS.mm | 2020-10-12 |
| 130 | A Unified Framework For Detecting Audio Adversarial Examples | XIA DU et. al. | In this paper, we propose a unified adversarial detection framework for detecting adaptive audio adversarial examples, which combines noise padding with sound reverberation. | CS.mm | 2020-10-12 |
| 131 | DIPDefend: Deep Image Prior Driven Defense Against Adversarial Examples | TAO DAI et. al. | Motivated by deep image prior that can capture rich image statistics from a single image, we propose an effective Deep Image Prior Driven Defense (DIPDefend) method against adversarial examples. | CS.mm | 2020-10-12 |
| 132 | Defending Adversarial Examples Via DNN Bottleneck Reinforcement | WENQING LIU et. al. | In order to reinforce the information bottleneck,we introduce the multi-scale low-pass objective and multi-scale high-frequency communication for better frequency steering in the network. | CS.mm | 2020-10-12 |
| 133 | Adversarial Bipartite Graph Learning For Video Domain Adaptation | YADAN LUO et. al. | To overcome this limitation, in this paper, we learn a domain-agnostic video classifier instead of learning domain-invariant representations, and propose an Adversarial Bipartite Graph (ABG) learning framework which directly models the source-target interactions with a network topology of the bipartite graph. | CS.mm | 2020-10-12 |
| 134 | Towards Understanding Pixel Vulnerability Under Adversarial Attacks For Images | HE ZHAO et. al. | Derived from the information-theoretic perspective, we propose a probabilistic approach for automatically finding the pixel vulnerability of an image, which is compatible with and improves over many existing adversarial attacks. | CS.arxiv | 2020-10-12 |
| 135 | MGAAttack: Toward More Query-efficient Black-box Attack By Microbial Genetic Algorithm | LINA WANG et. al. | To address the efficiency of querying in black-box attack, we propose a novel attack, called MGAAttack, which is a query-efficient and gradient-free black-box attack without obtaining any knowledge of the target model. | CS.mm | 2020-10-12 |
| 136 | Multi-modal Multi-relational Feature Aggregation Network For Medical Knowledge Representation Learning | YINGYING ZHANG et. al. | In this paper, we propose a Multi-modal Multi-Relational Feature Aggregation Network (MMRFAN) for medical knowledge representation learning. | CS.mm | 2020-10-12 |
| 137 | Shape-Texture Debiased Neural Network Training | YINGWEI LI et. al. | Motivated by this observation, we develop a simple algorithm for shape-texture debiased learning. | CS.arxiv | 2020-10-12 |
| 138 | MMNet: Multi-Stage And Multi-Scale Fusion Network For RGB-D Salient Object Detection | GUIBIAO LIAO et. al. | To effectively capture multi-scale cross-modal fusion features, this paper proposes a novel Multi-stage and Multi-Scale Fusion Network (MMNet), which consists of a cross-modal multi-stage fusion module (CMFM) and a bi-directional multi-scale decoder (BMD). | CS.mm | 2020-10-12 |
| 139 | Semantic Consistency Guided Instance Feature Alignment For 2D Image-Based 3D Shape Retrieval | HEYU ZHOU et. al. | In this paper, we propose a novel semantic consistency guided instance feature alignment network (SC-IFA) to address these limitations. | CS.mm | 2020-10-12 |
| 140 | IF-Defense: 3D Adversarial Point Cloud Defense Via Implicit Function Based Restoration | ZIYI WU et. al. | In this paper, we propose a novel 3D adversarial point cloud defense method leveraging implicit function based restoration (IF-Defense) to address both the aforementioned attacks. | CS.arxiv | 2020-10-11 |
| 141 | A Progressive Conditional Generative Adversarial Network For Generating Dense And Colored 3D Point Clouds | MOHAMMAD SAMIUL ARSHAD et. al. | In this paper, we introduce a novel conditional generative adversarial network that creates dense 3D point clouds, with color, for assorted classes of objects in an unsupervised manner. | CS.arxiv | 2020-10-11 |
| 142 | Shape-aware Generative Adversarial Networks For Attribute Transfer | LEI LUO et. al. | In this paper, we introduce a shape-aware GAN model that is able to preserve shape when transferring attributes, and propose its application to some real-world domains. | CS.arxiv | 2020-10-11 |
| 143 | MammoGANesis: Controlled Generation Of High-Resolution Mammograms For Radiology Education | CYRIL ZAKKA et. al. | In this paper we train a generative adversarial network (GAN) to synthesize 512 x 512 high-resolution mammograms. | CS.arxiv | 2020-10-11 |
| 144 | Regularizing Neural Networks Via Adversarial Model Perturbation | YAOWEI ZHENG et. al. | Motivated by this understanding, we propose a new regularization scheme. | CS.arxiv | 2020-10-10 |
| 145 | Is It Time To Redefine The Classification Task For Deep Neural Networks? | KEJI HAN et. al. | This paper defines the interval-label classification task for the deep classification system, whose labels are predefined non-overlapping intervals, instead of a fixed value (hard label) or probability vector (soft label). | CS.arxiv | 2020-10-10 |
| 146 | Baseline System Of Voice Conversion Challenge 2020 With Cyclic Variational Autoencoder And Parallel WaveGAN | PATRICK LUMBAN TOBING et. al. | In this paper, we present a description of the baseline system of Voice Conversion Challenge (VCC) 2020 with a cyclic variational autoencoder (CycleVAE) and Parallel WaveGAN (PWG), i.e., CycleVAEPWG. | CS.arxiv | 2020-10-09 |
| 147 | Be Your Own Best Competitor! Multi-Branched Adversarial Knowledge Transfer | MAHDI GHORBANI et. al. | Recently, several compression methods have been proposed to diminish the heavy computational burden and memory consumption. | CS.arxiv | 2020-10-09 |
| 148 | Improved Techniques For Model Inversion Attacks | SI CHEN et. al. | We present a variety of new techniques that can significantly boost the performance of MI attacks against DNNs. | CS.arxiv | 2020-10-08 |
| 149 | Improve Adversarial Robustness Via Weight Penalization On Classification Layer | CONG XU et. al. | These findings reveal the limitations of the existing approaches and lead us to develop a novel light-weight-penalized defensive method, which is simple and has a good scalability. | CS.arxiv | 2020-10-08 |
| 150 | Deep-Masking Generative Network: A Unified Framework For Background Restoration From Superimposed Images | XIN FENG et. al. | In this work we present the Deep-Masking Generative Network (DMGN), which is a unified framework for background restoration from the superimposed images and is able to cope with different types of noise. | CS.arxiv | 2020-10-08 |
| 151 | On The Evaluation Of Generative Adversarial Networks By Discriminative Models | AMIRSINA TORFI et. al. | In this work, we leverage Siamese neural networks to propose a domain-agnostic evaluation metric: (1) with a qualitative evaluation that is consistent with human evaluation, (2) that is robust relative to common GAN issues such as mode dropping and invention, and (3) does not require any pretrained classifier. | CS.arxiv | 2020-10-07 |
| 152 | Double Targeted Universal Adversarial Perturbations | PHILIPP BENZ et. al. | We introduce a double targeted universal adversarial perturbations (DT-UAPs) to bridge the gap between the instance-discriminative image-dependent perturbations and the generic universal perturbations. | CS.arxiv | 2020-10-07 |
| 153 | Not All Datasets Are Born Equal: On Heterogeneous Data And Adversarial Examples | EDEN LEVY et. al. | In this paper, we introduce an optimization framework for identifying adversarial perturbations in heterogeneous input spaces. | CS.arxiv | 2020-10-07 |
| 154 | CD-UAP: Class Discriminative Universal Adversarial Perturbation | CHAONING ZHANG et. al. | In this work, we propose a new universal attack method to generate a single perturbation that fools a target network to misclassify only a chosen group of classes, while having limited influence on the remaining classes. | CS.arxiv | 2020-10-07 |
| 155 | Batch Normalization Increases Adversarial Vulnerability: Disentangling Usefulness And Robustness Of Model Features | PHILIPP BENZ et. al. | With a classifier DNN defined as a feature set $F$ we propose a framework for disentangling $F$ robust usefulness into $F$ usefulness and $F$ robustness. | CS.arxiv | 2020-10-07 |
| 156 | Adversarial Attacks On Audio Source Separation | NAOYA TAKAHASHI et. al. | In this work, we reformulate various adversarial attack methods for the audio source separation problem and intensively investigate them under different attack conditions and target models. | CS.arxiv | 2020-10-07 |
| 157 | Domain Adversarial Neural Networks For Dysarthric Speech Recognition | DOMINIKA WOSZCZYK et. al. | The experiments conducted in this paper show that DANN achieves an absolute recognition rate of 74.91% and outperforms the baseline by 12.18%. | CS.arxiv | 2020-10-07 |
| 158 | Global Optimization Of Objective Functions Represented By ReLU Networks | CHRISTOPHER A. STRONG et. al. | We propose strategies to extend existing verifiers to provide provably optimal adversarial examples. | CS.arxiv | 2020-10-07 |
| 159 | DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization For High Spatial Resolution Remote Sensing Image Retrieval | YUN CAO et. al. | Aiming at obtaining more accurate HSR-RSI retrieval performance with small training samples, we develop a deep metric learning approach with generative adversarial network regularization (DML-GANR) for HSR-RSI retrieval. | CS.arxiv | 2020-10-06 |
| 160 | BAAAN: Backdoor Attacks Against Autoencoder And GAN-Based Machine Learning Models | AHMED SALEM et. al. | In this work, we explore one of the most severe attacks against machine learning models, namely the backdoor attack, against both autoencoders and GANs. | CS.arxiv | 2020-10-06 |
| 161 | Disentangled Generative Causal Representation Learning | XINWEI SHEN et. al. | This paper proposes a Disentangled gEnerative cAusal Representation (DEAR) learning method. | CS.arxiv | 2020-10-06 |
| 162 | Adversarial Patch Attacks On Monocular Depth Estimation Networks | KOICHIRO YAMANAKA et. al. | To reveal this limitation, we propose a method of adversarial patch attack on monocular depth estimation. | CS.arxiv | 2020-10-06 |
| 163 | Sample Weighting As An Explanation For Mode Collapse In Generative Adversarial Networks | AKSEL WILHELM WOLD EIDE et. al. | We present both theory and empirical results suggesting that this makes NS-GAN prone to mode dropping. | CS.arxiv | 2020-10-05 |
| 164 | Towards Generalized And Distributed Privacy-Preserving Representation Learning | SHEIKH SHAMS AZAM et. al. | We propose a novel framework, Exclusion-Inclusion Generative Adversarial Network (EIGAN), that generalizes existing adversarial privacy-preserving representation learning (PPRL) approaches to generate data encodings that account for multiple possibly overlapping ally and adversary targets. | CS.arxiv | 2020-10-05 |
| 165 | Providing Actionable Feedback In Hiring Marketplaces Using Generative Adversarial Networks | DANIEL NEMIROVSKY et. al. | In this work, we demonstrate how, by applying a newly introduced method based on Generative Adversarial Networks (GANs), we are able to overcome these limitations and provide actionable feedback in real-time to candidates in production settings. | CS.arxiv | 2020-10-05 |
| 166 | Adversarial Grammatical Error Correction | VIPUL RAHEJA et. al. | In this work, we present an adversarial learning approach to GEC, using the generator-discriminator framework. | CS.arxiv | 2020-10-05 |
| 167 | Conditional Generative Adversarial Networks To Model Urban Outdoor Air Pollution | JAMAL TOUTOUH | In order to deal with such a lack of data, we propose to train models able to generate synthetic nitrogen dioxide daily time series according to a given classification that will allow an unlimited generation of realistic data. | CS.arxiv | 2020-10-05 |
| 168 | Multi-level Feature Learning On Embedding Layer Of Convolutional Autoencoders And Deep Inverse Feature Learning For Image Clustering | BEHZAD GHAZANFARI et. al. | This paper introduces Multi-Level feature learning alongside the Embedding layer of Convolutional Autoencoder (CAE-MLE) as a novel approach in deep clustering. | CS.arxiv | 2020-10-05 |
| 169 | Offline Learning For Planning: A Summary | GIORGIO ANGELOTTI et. al. | In this paper we adumbrate the ideas motivating the development of the state-of-the-art offline learning baselines. | CS.arxiv | 2020-10-05 |
| 170 | SMILE: Semantically-guided Multi-attribute Image And Layout Editing | ANDRÉS ROMERO et. al. | In this paper, we successfully exploit a multimodal representation that handles all attributes, be it guided by random noise or exemplar images, while only using the underlying domain information of the target domain. | CS.arxiv | 2020-10-05 |
| 171 | Understanding Classifier Mistakes With Generative Models | LAËTITIA SHAO et. al. | In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize. | CS.arxiv | 2020-10-05 |
| 172 | A Panda? No, It’s A Sloth: Slowdown Attacks On Adaptive Multi-Exit Neural Network Inference | SANGHYUN HONG et. al. | In this paper, we conduct a systematic evaluation of this threat by experimenting with three generic multi-exit DNNs (based on VGG16, MobileNet, and ResNet56) and a custom multi-exit architecture, on two popular image classification benchmarks (CIFAR-10 and Tiny ImageNet). | CS.arxiv | 2020-10-05 |
| 173 | Detecting Misclassification Errors In Neural Networks With A Gaussian Process Model | XIN QIU et. al. | This paper presents a new framework that produces more reliable confidence scores for detecting misclassification errors. | CS.arxiv | 2020-10-05 |
| 174 | Winning Lottery Tickets In Deep Generative Models | NEHA MUKUND KALIBHAT et. al. | In this paper, we confirm the existence of winning tickets in deep generative models such as GANs and VAEs. | CS.arxiv | 2020-10-05 |
| 175 | Geometry-aware Instance-reweighted Adversarial Training | JINGFENG ZHANG et. al. | In this paper, we show this direction is also promising. | CS.arxiv | 2020-10-04 |
| 176 | A Study For Universal Adversarial Attacks On Texture Recognition | YINGPENG DENG et. al. | Given the outstanding progress that convolutional neural networks (CNNs) have made on natural image classification and object recognition problems, it is shown that deep learning methods can achieve very good recognition performance on many texture datasets. | CS.arxiv | 2020-10-04 |
| 177 | Unsupervised Shadow Removal Using Target Consistency Generative Adversarial Network | CHAO TAN et. al. | In this paper, we develop a simple yet efficient target-consistency generative adversarial network (TC-GAN) for the shadow removal task in the unsupervised manner. | CS.arxiv | 2020-10-03 |
| 178 | MagGAN: High-Resolution Face Attribute Editing With Mask-Guided Generative Adversarial Network | YI WEI et. al. | We present Mask-guided Generative Adversarial Network (MagGAN) for high-resolution face attribute editing, in which semantic facial masks from a pre-trained face parser are used to guide the fine-grained image editing process. | CS.arxiv | 2020-10-03 |
| 179 | Spatial Frequency Bias In Convolutional Generative Adversarial Networks | MAHYAR KHAYATKHOEI et. al. | In this paper, we show that the ability of GANs to learn a distribution is significantly affected by the spatial frequency of the underlying carrier signal, that is, GANs have a bias against learning high spatial frequencies. | CS.arxiv | 2020-10-03 |
| 180 | Assisting The Adversary To Improve GAN Training | ANDREAS MUNK et. al. | We propose a method for improved training of generative adversarial networks (GANs). | CS.arxiv | 2020-10-03 |
| 181 | Does Network Width Really Help Adversarial Robustness? | BOXI WU et. al. | In this paper, we carefully examine the relation between network width and model robustness. | CS.arxiv | 2020-10-03 |
| 182 | Unsupervised Monocular Depth Estimation For Night-time Images Using Adversarial Domain Feature Adaptation | MADHU VANKADARI et. al. | In this paper, we look into the problem of estimating per-pixel depth maps from unconstrained RGB monocular night-time images which is a difficult task that has not been addressed adequately in the literature. | CS.arxiv | 2020-10-03 |
| 183 | Adversarial And Natural Perturbations For General Robustness | SADAF GULSHAD et. al. | In this paper we aim to explore the general robustness of neural network classifiers by utilizing adversarial as well as natural perturbations. | CS.arxiv | 2020-10-03 |
| 184 | A Geometry-Inspired Attack For Generating Natural Language Adversarial Examples | ZHAO MENG et. al. | In this paper, we propose a geometry-inspired attack for generating natural language adversarial examples. | CS.arxiv | 2020-10-03 |
| 185 | MGD-GAN: Text-to-Pedestrian Generation Through Multi-Grained Discrimination | SHENGYU ZHANG et. al. | In this paper, we investigate the problem of text-to-pedestrian synthesis, which has many potential applications in art, design, and video surveillance. | CS.arxiv | 2020-10-02 |
| 186 | $f$-GAIL: Learning $f$-Divergence For Generative Adversarial Imitation Learning | XIN ZHANG et. al. | In this work, we propose $f$-GAIL, a new generative adversarial imitation learning (GAIL) model, that automatically learns a discrepancy measure from the $f$-divergence family as well as a policy capable of producing expert-like behaviors. | CS.arxiv | 2020-10-02 |
| 187 | A Deep Genetic Programming Based Methodology For Art Media Classification Robust To Adversarial Perturbations | GUSTAVO OLAGUE et. al. | Therefore, this work presents a Deep Genetic Programming method, called Brain Programming, that competes with deep learning and studies the transferability of adversarial attacks using two artworks databases made by art experts. | CS.arxiv | 2020-10-02 |
| 188 | An Empirical Study Of DNNs Robustification Inefficacy In Protecting Visual Recommenders | VITO WALTER ANELLI et. al. | To answer these questions, we define a set of defense and attack settings, as well as recommender models, to empirically investigate the efficacy of defensive mechanisms. | CS.arxiv | 2020-10-02 |
| 189 | Encoded Prior Sliced Wasserstein AutoEncoder For Learning Latent Manifold Representations | SANJUKTA KRISHNAGOPAL et. al. | In this work, we introduce an Encoded Prior Sliced Wasserstein AutoEncoder (EPSWAE) wherein an additional prior-encoder network learns an unconstrained prior to match the encoded data manifold. | CS.arxiv | 2020-10-02 |
| 190 | Evaluating A Generative Adversarial Framework For Information Retrieval | AMEET DESHPANDE et. al. | Motivated by our findings, we propose two models influenced by self-contrastive estimation and co-training which outperform IRGAN on two out of the three tasks considered. | CS.arxiv | 2020-10-01 |
| 191 | Tabular GANs For Uneven Distribution | INSAF ASHRAPOV | We will review and examine some recent papers about tabular GANs in action. | CS.arxiv | 2020-10-01 |
| 192 | Cycle-Consistent Adversarial Autoencoders For Unsupervised Text Style Transfer | YUFANG HUANG et. al. | In this paper, we propose a novel neural approach to unsupervised text style transfer, which we refer to as Cycle-consistent Adversarial autoEncoders (CAE) trained from non-parallel data. | CS.arxiv | 2020-10-01 |
| 193 | RDSGAN: Rank-based Distant Supervision Relation Extraction With Generative Adversarial Framework | GUOQING LUO et. al. | In this paper, we propose a novel generative neural framework named RDSGAN (Rank-based Distant Supervision GAN) which automatically generates valid instances for distant supervision relation extraction. | CS.arxiv | 2020-09-30 |
| 194 | Towards Self-learning Edge Intelligence In 6G | YONG XIAO et. al. | In this article, we identify the key requirements and challenges of edge-native AI in 6G. | CS.arxiv | 2020-09-30 |
| 195 | MaterialGAN: Reflectance Capture Using A Generative SVBRDF Model | YU GUO et. al. | In this work, we present MaterialGAN, a deep generative convolutional network based on StyleGAN2, trained to synthesize realistic SVBRDF parameter maps. | CS.arxiv | 2020-09-30 |
| 196 | CardioGAN: Attentive Generative Adversarial Network With Dual Discriminators For Synthesis Of ECG From PPG | PRITAM SARKAR et. al. | In order to tackle this problem, we propose CardioGAN, an adversarial model which takes PPG as input and generates ECG as output. | CS.arxiv | 2020-09-30 |
| 197 | 3D Dense Geometry-Guided Facial Expression Synthesis By Adversarial Learning | RUMEYSA BODUR et. al. | Unlike previous methods using Generative Adversarial Networks (GAN), which rely on cycle-consistency loss or sparse geometry (landmarks) loss for expression synthesis, we propose a novel GAN framework to exploit 3D dense (depth and surface normals) information for expression manipulation. | CS.arxiv | 2020-09-30 |
| 198 | Adversarial Semi-Supervised Multi-Domain Tracking | KOUROSH MESHGI et. al. | We propose a semi-supervised learning scheme to separate domain-invariant and domain-specific features using adversarial learning, to encourage mutual exclusion between them, and to leverage self-supervised learning for enhancing the shared features using the unlabeled reservoir. | CS.arxiv | 2020-09-30 |
| 199 | TinyGAN: Distilling BigGAN For Conditional Image Generation | TING-YUN CHANG et. al. | To reduce the model size, we propose a black-box knowledge distillation framework for compressing GANs, which highlights a stable and efficient training process. | CS.arxiv | 2020-09-29 |
| 200 | ImdpGAN: Generating Private And Specific Data With Generative Adversarial Networks | SAURABH GUPTA et. al. | To address these issues, we propose imdpGAN – an information maximizing differentially private Generative Adversarial Network. | CS.arxiv | 2020-09-29 |
| 201 | Bilateral Asymmetry Guided Counterfactual Generating Network For Mammogram Classification | CHU-RAN WANG et. al. | Motivated by the symmetric prior that the lesions on one side of breasts rarely appear in the corresponding areas on the other side, given a diseased image, we can explore a counterfactual problem that how would the features have behaved if there were no lesions in the image, so as to identify the lesion areas. | CS.arxiv | 2020-09-29 |
| 202 | EEG To FMRI Synthesis: Is Deep Learning A Candidate? | DAVID CALHAS et. al. | The code used in this manuscript is available in Github and the datasets are open source. | CS.arxiv | 2020-09-29 |
| 203 | Neural Topic Modeling With Cycle-Consistent Adversarial Training | XUEMENG HU et. al. | To overcome such limitations, we propose Topic Modeling with Cycle-consistent Adversarial Training (ToMCAT) and its supervised version sToMCAT. | CS.arxiv | 2020-09-29 |
| 204 | Fast Fréchet Inception Distance | ALEXANDER MATHIASEN et. al. | We present a novel algorithm, FastFID, which allows fast computation and backpropagation for FID. | CS.arxiv | 2020-09-29 |
| 205 | Realistic Image Normalization For Multi-Domain Segmentation | PIERRE-LUC DELISLE et. al. | This paper proposes to revisit the conventional image normalization approach by instead learning a common normalizing function across multiple datasets. | CS.arxiv | 2020-09-29 |
| 206 | Toward Privacy And Utility Preserving Image Representation | AHMADREZA MOSALLANEZHAD et. al. | In this paper, we study the novel problem of creating privacy-preserving image representations with respect to a given utility task by proposing a principled framework called the Adversarial Image Anonymizer (AIA). | CS.arxiv | 2020-09-29 |
| 207 | EvolGAN: Evolutionary Generative Adversarial Networks | BAPTISTE ROZIERE et. al. | We propose to use a quality estimator and evolutionary methods to search the latent space of generative adversarial networks trained on small, difficult datasets, or both. | CS.arxiv | 2020-09-28 |
| 208 | Anomaly Detection And Sampling Cost Control Via Hierarchical GANs | CHEN ZHONG et. al. | In this work, we study anomaly detection by considering the detection of threshold crossings in a stochastic time series without the knowledge of its statistics. | CS.arxiv | 2020-09-28 |
| 209 | Graph Adversarial Networks: Protecting Information Against Adversarial Attacks | PEIYUAN LIAO et. al. | To counter this, we propose a minimax game between the desired GNN encoder and the worst-case attacker. | CS.arxiv | 2020-09-28 |
| 210 | Balancing Thermal Comfort Datasets: We GAN, But Should We? | MATIAS QUINTANA et. al. | This paper investigates the various thermal comfort dataset class balancing techniques from the literature and proposes a modified conditional Generative Adversarial Network (GAN), $\texttt{comfortGAN}$, to address this imbalance scenario. | CS.arxiv | 2020-09-28 |
| 211 | Adversarial Robustness Of Stabilized NeuralODEs Might Be From Obfuscated Gradients | YIFEI HUANG et. al. | In this paper we introduce a provably stable architecture for Neural Ordinary Differential Equations (ODEs) which achieves non-trivial adversarial robustness under white-box adversarial attacks even when the network is trained naturally. | CS.arxiv | 2020-09-28 |
| 212 | Recognition And Synthesis Of Object Transport Motion | CONNOR DALY | By exploring recent developments in the concept of Generative Adversarial Models (GANs), specifically the Wasserstein GAN, this project outlines a model that is able to successfully generate lifelike object transportation motions, with the generated samples displaying varying styles and transport strategies. | CS.arxiv | 2020-09-27 |
| 213 | RoGAT: A Robust GNN Combined Revised GAT With Adjusted Graphs | XIANCHEN ZHOU et. al. | Robust GAT(RoGAT) is proposed to improve the robustness of GNNs in this paper, . | CS.arxiv | 2020-09-27 |
| 214 | VATLD: A Visual Analytics System To Assess, Understand And Improve Traffic Light Detection | LIANG GOU et. al. | In this work, we propose a visual analytics system, VATLD, equipped with a disentangled representation learning and semantic adversarial learning, to assess, understand, and improve the accuracy and robustness of traffic light detectors in autonomous driving applications. | CS.arxiv | 2020-09-27 |
| 215 | Local And Non-local Dependency Learning And Emergence Of Rule-like Representations In Speech Data By Deep Convolutional Generative Adversarial Networks | GAŠPER BEGUŠ | We extend this approach to test learning of local and non-local phonological processes that include approximations of morphological processes. | CS.arxiv | 2020-09-26 |
| 216 | Decision-Aware Conditional GANs For Time Series Data | HE SUN et. al. | We introduce the decision-aware time-series conditional generative adversarial network (DAT-CGAN) as a method for time-series generation. | CS.arxiv | 2020-09-26 |
| 217 | Beneficial Perturbations Network For Defending Adversarial Examples | SHIXIAN WEN et. al. | Here, we present a new solution to ease these three difficulties – Beneficial perturbation Networks (BPN). | CS.arxiv | 2020-09-26 |
| 218 | Differentially Private Adversarial Robustness Through Randomized Perturbations | NAN XU et. al. | In this paper, we study adversarial robustness through randomized perturbations, which has two immediate advantages: (1) by ensuring that substitution likelihood is weighted by the proximity to the original word, we circumvent optimizing the worst case guarantees and achieve performance gains; and (2) the calibrated randomness imparts differentially-private model training, which additionally improves robustness against adversarial attacks on the model outputs. | CS.arxiv | 2020-09-26 |
| 219 | A Generic Framework For Clustering Vehicle Motion Trajectories | FAZELEH S. HOSEINI et. al. | To address this issue, we propose an effective non-parametric trajectory clustering framework consisting of five stages: (1) aligning trajectories and quantifying their pairwise temporal dissimilarities, (2) embedding the trajectory-based dissimilarities into a vector space, (3) extracting transitive relations, (4) embedding the transitive relations into a new vector space, and (5) clustering the trajectories with an optimal number of clusters. | CS.arxiv | 2020-09-25 |
| 220 | Generating Realistic COVID19 X-rays With A Mean Teacher + Transfer Learning GAN | SUMEET MENON et. al. | We present a novel Mean Teacher + Transfer GAN (MTT-GAN) that generates COVID19 chest X-ray images of high quality. | CS.arxiv | 2020-09-25 |
| 221 | Deep Adversarial Transition Learning Using Cross-Grafted Generative Stacks | JINYONG HOU et. al. | In this paper, we present a novel deep adversarial transition learning (DATL) framework that bridges the domain gap by projecting the source and target domains into intermediate, transitional spaces through the employment of adjustable, cross-grafted generative network stacks and effective adversarial learning between transitions. | CS.arxiv | 2020-09-25 |
| 222 | Attention Meets Perturbations: Robust And Interpretable Attention With Adversarial Training | SHUNSUKE KITADA et. al. | In this paper, we propose a new general training technique for NLP tasks, using AT for attention (Attention AT) and more interpretable adversarial training for attention (Attention iAT). | CS.arxiv | 2020-09-25 |
| 223 | Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights | SHU HU et. al. | In this work, we show that GAN synthesized faces can be exposed with the inconsistent corneal specular highlights between two eyes. | CS.arxiv | 2020-09-24 |
| 224 | GANs With Variational Entropy Regularizers: Applications In Mitigating The Mode-Collapse Issue | PIRAZH KHORRAMSHAHI et. al. | To tackle this issue, we take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity. | CS.arxiv | 2020-09-24 |
| 225 | Graph Sparsification With Generative Adversarial Network | HANG-YANG WU et. al. | In this study, we propose a novel method called GSGAN, which is able to sparsify networks for community detection tasks. | CS.arxiv | 2020-09-24 |
| 226 | Adversarial Examples In Deep Learning For Multivariate Time Series Regression | GAUTAM RAJ MODE et. al. | In this work, we leverage existing adversarial attack generation techniques from the image classification domain and craft adversarial multivariate time series examples for three state-of-the-art deep learning regression models, specifically Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). | CS.arxiv | 2020-09-24 |
| 227 | Improving Query Efficiency Of Black-box Adversarial Attack | YANG BAI et. al. | Therefore, in order to improve query efficiency, we explore the distribution of adversarial examples around benign inputs with the help of image structure information characterized by a Neural Process, and propose a Neural Process based black-box adversarial attack (NP-Attack) in this paper. | CS.arxiv | 2020-09-24 |
| 228 | What Is The Reward For Handwriting? — Handwriting Generation By Imitation Learning | KEISUKE KANDA et. al. | In this study, we use a reinforcement learning (RL) framework to realize handwriting generation with the careful future planning ability. | CS.arxiv | 2020-09-23 |
| 229 | Topology-Aware Generative Adversarial Network For Joint Prediction Of Multiple Brain Graphs From A Single Brain Graph | ALAA BESSADOK et. al. | Several works based on Generative Adversarial Networks (GAN) have been recently proposed to predict a set of medical images from a single modality (e.g, FLAIR MRI from T1 MRI). | CS.arxiv | 2020-09-23 |
| 230 | Generative Model Without Prior Distribution Matching | CONG GENG et. al. | To mitigate this problem, we propose to let the prior match the embedding distribution rather than imposing the latent variables to fit the prior. | CS.arxiv | 2020-09-23 |
| 231 | Semantics-Preserving Adversarial Training | WONSEOK LEE et. al. | In this paper, we identify an overlooked problem of adversarial training in that these adversarial examples often have different semantics than the original data, introducing unintended biases into the model. | CS.arxiv | 2020-09-23 |
| 232 | Residual Embedding Similarity-Based Network Selection For Predicting Brain Network Evolution Trajectory From A Single Observation | AHMET SERKAN GOKTAS et. al. | To overcome this major drawback, we propose Residual Embedding Similarity-Based Network selection (RESNets) for predicting brain network evolution trajectory from a single timepoint. | CS.arxiv | 2020-09-23 |
| 233 | Enhancing Mixup-based Semi-Supervised Learning With Explicit Lipschitz Regularization | PRASHNNA KUMAR GYAWALI et. al. | In this paper, we offer a theoretically substantiated proposition that mixup improves the smoothness of the neural function by bounding the Lipschitz constant of the gradient function of the neural networks. | CS.arxiv | 2020-09-23 |
| 234 | A Partial Break Of The Honeypots Defense To Catch Adversarial Attacks | NICHOLAS CARLINI | The authors of the original paper have amended the defense in their CCS’20 paper to mitigate this attacks. | CS.arxiv | 2020-09-23 |
| 235 | Detection Of Iterative Adversarial Attacks Via Counter Attack | MATTHIAS ROTTMANN et. al. | In this work, we demonstrate that such iterative minimization attacks can by used as detectors themselves. | CS.arxiv | 2020-09-23 |
| 236 | A Generative Adversarial Approach With Residual Learning For Dust And Scratches Artifacts Removal | IONUŢ MIRONICĂ | In this paper, we present a GAN based method that is able to remove dust and scratches errors from film scans. | CS.arxiv | 2020-09-22 |
| 237 | DeepTag: Robust Image Tagging For DeepFake Provenance | RUN WANG et. al. | In this paper, we investigated the potentials of image tagging in serving the DeepFake provenance. | CS.arxiv | 2020-09-21 |
| 238 | MFIF-GAN: A New Generative Adversarial Network For Multi-Focus Image Fusion | YICHENG WANG et. al. | In this paper,we propose a network termed MFIF-GAN to attenuate the DSE by generating focus maps in which the foreground region are correctly larger than the corresponding objects. | CS.arxiv | 2020-09-21 |
| 239 | Stereopagnosia: Fooling Stereo Networks With Adversarial Perturbations | ALEX WONG et. al. | We study the effect of adversarial perturbations of images on the estimates of disparity by deep learning models trained for stereo. | CS.arxiv | 2020-09-21 |
| 240 | Scalable Adversarial Attack On Graph Neural Networks With Alternating Direction Method Of Multipliers | BOYUAN FENG et. al. | In this work, we propose, SAG, the first scalable adversarial attack method with Alternating Direction Method of Multipliers (ADMM). | CS.arxiv | 2020-09-21 |
| 241 | Generating Adversarial Yet Inconspicuous Patches With A Single Image | JINQI LUO et. al. | To over-come these challenges, we propose an approach to gen-erate adversarial yet inconspicuous patches with onesingle image. | CS.arxiv | 2020-09-21 |
| 242 | Crafting Adversarial Examples For Deep Learning Based Prognostics (Extended Version) | GAUTAM RAJ MODE et. al. | In this paper, we adopt the adversarial example crafting techniques from the computer vision domain and apply them to the PHM domain. | CS.arxiv | 2020-09-21 |
| 243 | Uncertainty-aware Attention Graph Neural Network For Defending Adversarial Attacks | BOYUAN FENG et. al. | Motivated by these observations, we propose UAG, the first systematic solution to defend adversarial attacks on GNNs through identifying and exploiting hierarchical uncertainties in GNNs. | CS.arxiv | 2020-09-21 |
| 244 | On The Performance Of Generative Adversarial Network (GAN) Variants: A Clinical Data Study | JAESUNG YOO et. al. | Various types of GANs are being researched with different insights, resulting in a diverse family of GANs with a better performance in each generation. | CS.arxiv | 2020-09-20 |
| 245 | Semi-supervised Semantic Segmentation Of Prostate And Organs-at-Risk On 3D Pelvic CT Images | ZHUANGZHUANG ZHANG et. al. | Taking automated segmentation of OARs as a case study, we developed a novel semi-supervised adversarial deep learning approach to support medical image data processing and modeling where training data may be insufficient. | CS.arxiv | 2020-09-20 |
| 246 | Addressing Reward Bias In Adversarial Imitation Learning With Neutral Reward Functions | ROHIT JENA et. al. | We provide a theoretical sketch of why existing reward functions would fail in imitation learning scenarios in task based environments with multiple terminal states. | CS.arxiv | 2020-09-20 |
| 247 | Remote Sensing Image Fusion Based On Bayesian GAN | JUNFU CHEN et. al. | Inspired by the efficient arameter space posteriori sampling of Bayesian neural networks, in this paper we propose a Bayesian Generative Adversarial Network based on Preconditioned Stochastic Gradient Langevin Dynamics (PGSLD-BGAN) to improve pan-sharpening tasks. | CS.arxiv | 2020-09-20 |
| 248 | Subverting Privacy-Preserving GANs: Hiding Secrets In Sanitized Images | KANG LIU et. al. | In this work, we question the rigor of such checks by subverting existing privacy-preserving GANs for facial expression recognition. | CS.arxiv | 2020-09-19 |
| 249 | Adversarial Exposure Attack On Diabetic Retinopathy Imagery | YUPENG CHENG et. al. | In this paper, we study this problem from the viewpoint of adversarial attack and identify a totally new task, i.e., adversarial exposure attack generating adversarial images by tuning image exposure to mislead the DNNs with significantly high transferability. | CS.arxiv | 2020-09-19 |
| 250 | It’s Raining Cats Or Dogs? Adversarial Rain Attack On DNN Perception | LIMING ZHAI et. al. | To this end, in this paper, we start from a new perspective and propose to combine two totally different studies, i.e., rainy image synthesis and adversarial attack. | CS.arxiv | 2020-09-19 |
| 251 | Learning To Attack: Towards Textual Adversarial Attacking In Real-world Situations | YUAN ZANG et. al. | To tackle this problem, we propose a reinforcement learning based attack model, which can learn from attack history and launch attacks more efficiently. | CS.arxiv | 2020-09-19 |
| 252 | Efficient Certification Of Spatial Robustness | ANIAN RUOSS et. al. | In this work, we propose novel convex relaxations, which enable us, for the first time, to provide a certificate of robustness against spatial transformations. | CS.arxiv | 2020-09-19 |
| 253 | Conditional Image Generation With One-Vs-All Classifier | XIANGRUI XU et. al. | Instead of the real/fake discriminator used in vanilla GANs, we propose to extend the discriminator to a One-Vs-All classifier (GAN-OVA) that can distinguish each input data to its category label. | CS.arxiv | 2020-09-18 |
| 254 | DeltaGAN: Towards Diverse Few-shot Image Generation With Sample-Specific Delta | YAN HONG et. al. | In this work, we propose a novel Delta Generative Adversarial Network (DeltaGAN), which consists of a reconstruction subnetwork and a generation subnetwork. | CS.arxiv | 2020-09-18 |
| 255 | Time-series Imputation And Prediction With Bi-Directional Generative Adversarial Networks | MEHAK GUPTA et. al. | In this paper, we approach these issues by presenting a model for the combined task of imputing and predicting values for the irregularly observed and varying length time-series data with missing entries. | CS.arxiv | 2020-09-18 |
| 256 | Robust Decentralized Learning For Neural Networks | YAO ZHOU et. al. | In this work, we present a robust decentralized learning framework, Decent_BVA, using bias-variance based adversarial training via asymmetrical communications between each client and the server. | CS.arxiv | 2020-09-18 |
| 257 | SecDD: Efficient And Secure Method For Remotely Training Neural Networks | ILIA SUCHOLUTSKY et. al. | We leverage what are typically considered the worst qualities of deep learning algorithms – high computational cost, requirement for large data, no explainability, high dependence on hyper-parameter choice, overfitting, and vulnerability to adversarial perturbations – in order to create a method for the secure and efficient training of remotely deployed neural networks over unsecured channels. | CS.arxiv | 2020-09-18 |
| 258 | ExGAN: Adversarial Generation Of Extreme Samples | SIDDHARTH BHATIA et. al. | Hence, in this work, we propose ExGAN, a GAN-based approach to generate realistic and extreme samples. | CS.arxiv | 2020-09-17 |
| 259 | Crossing You In Style: Cross-modal Style Transfer From Music To Visual Arts | CHENG-CHE LEE et. al. | Assuming that musical features can be properly mapped to visual contents through semantic links between the two domains, we solve the music-to-visual style transfer problem in two steps: music visualization and style transfer. | CS.arxiv | 2020-09-17 |
| 260 | Vax-a-Net: Training-time Defence Against Adversarial Patch Attacks | T. GITTINGS et. al. | We present Vax-a-Net; a technique for immunizing convolutional neural networks (CNNs) against adversarial patch attacks (APAs). | CS.arxiv | 2020-09-17 |
| 261 | GeneraLight: Improving Environment Generalization Of Traffic Signal Control Via Meta Reinforcement Learning | CHANG LIU et. al. | In this paper, we design a novel traffic flow generator based on Wasserstein generative adversarial network to generate sufficient diverse and quality traffic flows and use them to build proper training and testing environments. | CS.arxiv | 2020-09-17 |
| 262 | Online Alternate Generator Against Adversarial Attacks | HAOFENG LI et. al. | To overcome the above issues, we propose a portable defense method, online alternate generator, which does not need to access or modify the parameters of the target networks. | CS.arxiv | 2020-09-17 |
| 263 | Large Norms Of CNN Layers Do Not Hurt Adversarial Robustness | YOUWEI LIANG et. al. | Based on our theorem, we propose a novel regularization method termed norm decay, which can effectively reduce the norms of CNN layers. | CS.arxiv | 2020-09-17 |
| 264 | Label Smoothing And Adversarial Robustness | CHAOHAO FU et. al. | We find that training model with label smoothing can easily achieve striking accuracy under most gradient-based attacks. | CS.arxiv | 2020-09-17 |
| 265 | SLGAN: Style- And Latent-guided Generative Adversarial Network For Desirable Makeup Transfer And Removal | DAICHI HORITA et. al. | Several related works have been proposed, mainly using generative adversarial networks (GAN). | CS.arxiv | 2020-09-16 |
| 266 | TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks | ALEXANDER GEIGER et. al. | In this paper, we propose TadGAN, an unsupervised anomaly detection approach built on Generative Adversarial Networks (GANs). | CS.arxiv | 2020-09-16 |
| 267 | CSI2Image: Image Reconstruction From Channel State Information Using Generative Adversarial Networks | SORACHI KATO et. al. | This study aims to find the upper limit of the wireless sensing capability of acquiring physical space information. | CS.arxiv | 2020-09-15 |
| 268 | MO-PaDGAN: Reparameterizing Engineering Designs For Augmented Multi-objective Optimization | WEI CHEN et. al. | To address these challenges, we propose MO-PaDGAN, which adds a Determinantal Point Processes based loss function to the generative adversarial network to simultaneously model diversity and (multi-variate) performance. | CS.arxiv | 2020-09-15 |
| 269 | Generative Models With Kernel Distance In Data Space | SZYMON KNOP et. al. | The objective of this paper is to construct a~model situated between above architectures, one that does not inherit their main weaknesses. | CS.arxiv | 2020-09-15 |
| 270 | Puzzle Mix: Exploiting Saliency And Local Statistics For Optimal Mixup | JANG-HYUN KIM et. al. | To this end, we propose Puzzle Mix, a mixup method for explicitly utilizing the saliency information and the underlying statistics of the natural examples. | CS.arxiv | 2020-09-15 |
| 271 | Improving Inversion And Generation Diversity In StyleGAN Using A Gaussianized Latent Space | JONAS WULFF et. al. | In this work, we propose to explicitly model the data distribution in latent space. | CS.arxiv | 2020-09-14 |
| 272 | Robust Deep Learning Ensemble Against Deception | WENQI WEI et. al. | This paper presents XEnsemble, a diversity ensemble verification methodology for enhancing the adversarial robustness of DNN models against deception caused by either adversarial examples or out-of-distribution inputs. | CS.arxiv | 2020-09-14 |
| 273 | Pairwise-GAN: Pose-based View Synthesis Through Pair-Wise Training | XUYANG SHEN et. al. | We conducted the experiments on five different loss functions on Pix2Pix to improve its performance, then followed by proposing a new network Pairwise-GAN in frontal facial synthesis. | CS.arxiv | 2020-09-13 |
| 274 | Identity-Based Patterns In Deep Convolutional Networks: Generative Adversarial Phonology And Reduplication | GAŠPER BEGUŠ | In this paper, we test whether a neural network can learn an identity-based pattern in speech called reduplication. | CS.arxiv | 2020-09-13 |
| 275 | Towards The Quantification Of Safety Risks In Deep Neural Networks | PEIPEI XU et. al. | In this paper, we define safety risks by requesting the alignment of the network’s decision with human perception. | CS.arxiv | 2020-09-13 |
| 276 | Multi-Spectral Image Synthesis For Crop/Weed Segmentation In Precision Farming | MULHAM FAWAKHERJI et. al. | In this work, we propose an alternative solution with respect to the common data augmentation techniques, applying it to the fundamental problem of crop/weed segmentation in precision farming. | CS.arxiv | 2020-09-12 |
| 277 | Certified Robustness Of Graph Classification Against Topology Attack With Randomized Smoothing | ZHIDONG GAO et. al. | In this work, we propose to build a smoothed graph classification model with certified robustness guarantee. | CS.arxiv | 2020-09-12 |
| 278 | Accurate And Intuitive Contextual Explanations Using Linear Model Trees | ADITYA LAHIRI et. al. | In this paper, we seek to significantly improve on both, the method used to generate the explanations and the nature of explanations produced. | CS.arxiv | 2020-09-11 |
| 279 | Inverse Mapping Of Face GANs | NICKY BAYAT et. al. | We train a ResNet architecture to recover a latent vector for a given face that can be used to generate a face nearly identical to the target. | CS.arxiv | 2020-09-11 |
| 280 | Applications Of Deep Neural Networks | JEFF HEATON | Application of these architectures to computer vision, time series, security, natural language processing (NLP), and data generation will be covered. | CS.arxiv | 2020-09-11 |
| 281 | Adversarial Score Matching And Improved Sampling For Image Generation | ALEXIA JOLICOEUR-MARTINEAU et. al. | We show that this apparent gap vanishes when denoising the final Langevin samples using the score network. | CS.arxiv | 2020-09-11 |
| 282 | Attribute-conditioned Layout GAN For Automatic Graphic Design | JIANAN LI et. al. | In this paper, we introduce Attribute-conditioned Layout GAN to incorporate the attributes of design elements for graphic layout generation by forcing both the generator and the discriminator to meet attribute conditions. | CS.arxiv | 2020-09-11 |
| 283 | Conditional Coupled Generative Adversarial Networks For Zero-Shot Domain Adaptation | JINGHUA WANG et. al. | In this paper, we tackle the challenging zero-shot domain adaptation (ZSDA) problem, where target-domain data is non-available in the training stage. | CS.arxiv | 2020-09-11 |
| 284 | Achieving Adversarial Robustness Via Sparsity | SHUFAN WANG et. al. | In this work, we theoretically prove that the sparsity of network weights is closely associated with model robustness. | CS.arxiv | 2020-09-11 |
| 285 | Defending Against Multiple And Unforeseen Adversarial Videos | SHAO-YUAN LO et. al. | In this paper, we propose one of the first defense solutions against multiple adversarial video types for video classification. | CS.arxiv | 2020-09-11 |
| 286 | Robust Neural Machine Translation: Modeling Orthographic And Interpunctual Variation | TOMS BERGMANIS et. al. | We propose a simple generative noise model to generate adversarial examples of ten different types. | CS.arxiv | 2020-09-11 |
| 287 | Adversarial Learning For Zero-shot Domain Adaptation | JINGHUA WANG et. al. | With the hypothesis that the shift between a given pair of domains is shared across tasks, we propose a new method for ZSDA by transferring domain shift from an irrelevant task (IrT) to the task of interest (ToI). | CS.arxiv | 2020-09-10 |
| 288 | Understanding The Role Of Individual Units In A Deep Neural Network | DAVID BAU et. al. | In this work, we present network dissection, an analytic framework to systematically identify the semantics of individual hidden units within image classification and image generation networks. | CS.arxiv | 2020-09-10 |
| 290 | Second Order Optimization For Adversarial Robustness And Interpretability | THEODOROS TSILIGKARIDIS et. al. | Inspired by the relationship between robustness and curvature, we propose a novel regularizer which incorporates first and second order information via a quadratic approximation to the adversarial loss. | CS.arxiv | 2020-09-10 |
| 291 | MU-GAN: Facial Attribute Editing Based On Multi-attention Mechanism | KE ZHANG et. al. | In this work, we propose a Multi-attention U-Net-based Generative Adversarial Network (MU-GAN). | CS.arxiv | 2020-09-09 |
| 292 | End-to-end Kernel Learning Via Generative Random Fourier Features | KUN FANG et. al. | To address this issue, we propose an end-to-end, one-stage kernel learning approach, called generative random Fourier features, which jointly learns the features and the classifier. | CS.arxiv | 2020-09-09 |
| 293 | SoK: Certified Robustness For Deep Neural Networks | LINYI LI et. al. | In this paper, we focus on these certifiably robust approaches and provide the first work to perform large-scale systematic analysis of different robustness verification and training approaches. | CS.arxiv | 2020-09-09 |
| 294 | Multilinear Latent Conditioning For Generating Unseen Attribute Combinations | MARKOS GEORGOPOULOS et. al. | To this end, we extend cVAE by introducing a multilinear latent conditioning framework that captures the multiplicative interactions between the attributes. | CS.arxiv | 2020-09-08 |
| 295 | Revisiting LSTM Networks For Semi-Supervised Text Classification Via Mixed Objective Function | DEVENDRA SINGH SACHAN et. al. | In this paper, we study bidirectional LSTM network for the task of text classification using both supervised and semi-supervised approaches. | CS.arxiv | 2020-09-08 |
| 296 | Adversarial Attack On Large Scale Graph | JINTANG LI et. al. | In this work, we propose an efficient Simplified Gradient-based Attack (SGA) framework to bridge this gap. | CS.arxiv | 2020-09-07 |
| 297 | Why Spectral Normalization Stabilizes GANs: Analysis And Improvements | ZINAN LIN et. al. | In this work, we show that SN controls two important failure modes of GAN training: exploding and vanishing gradients. | CS.arxiv | 2020-09-06 |
| 298 | A Generative Adversarial Approach To ECG Synthesis And Denoising | KAROL ANTCZAK | In this paper we present an approach to use GAN to produce realistically looking ECG signals. | CS.arxiv | 2020-09-06 |
| 299 | Detection Defense Against Adversarial Attacks With Saliency Map | DENGPAN YE et. al. | In this paper, we discuss the saliency map method from the view of enhancing model interpretability, it is similar to introducing the mechanism of the attention to the model, so as to comprehend the progress of object identification by the deep networks. | CS.arxiv | 2020-09-06 |
| 300 | Dynamically Computing Adversarial Perturbations For Recurrent Neural Networks | SHANKAR A. DEKA et. al. | We provide both in this paper. | CS.arxiv | 2020-09-06 |
| 301 | Bluff: Interactively Deciphering Adversarial Attacks On Deep Neural Networks | NILAKSH DAS et. al. | We present Bluff, an interactive system for visualizing, characterizing, and deciphering adversarial attacks on vision-based neural networks. | CS.arxiv | 2020-09-05 |
| 302 | Examining Machine Learning For 5G And Beyond Through An Adversarial Lens | MUHAMMAD USAMA et. al. | In this article, we present a cautionary perspective on the use of AI/ML in the 5G context by highlighting the adversarial dimension spanning multiple types of ML (supervised/unsupervised/RL) and support this through three case studies. | CS.arxiv | 2020-09-05 |
| 303 | Dual Manifold Adversarial Robustness: Defense Against Lp And Non-Lp Adversarial Attacks | WEI-AN LIN et. al. | To this end, we construct an On-Manifold ImageNet (OM-ImageNet) dataset by projecting the ImageNet samples onto the manifold learned by StyleGSN. | CS.arxiv | 2020-09-05 |
| 304 | TiVGAN: Text To Image To Video Generation With Step-by-Step Evolutionary Generator | DOYEON KIM et. al. | We propose a novel training framework, Text-to-Image-to-Video Generative Adversarial Network (TiVGAN), which evolves frame-by-frame and finally produces a full-length video. | CS.arxiv | 2020-09-04 |
| 305 | MIPGAN — Generating Robust And High Quality Morph Attacks Using Identity Prior Driven GAN | HAOYU ZHANG et. al. | We present a new approach for generating robust attacks extending our earlier framework for generating face morphs. | CS.arxiv | 2020-09-03 |
| 306 | Synthetic-to-Real Unsupervised Domain Adaptation For Scene Text Detection In The Wild | WEIJIA WU et. al. | To address the severe domain distribution mismatch, we propose a synthetic-to-real domain adaptation method for scene text detection, which transfers knowledge from synthetic data (source domain) to real data (target domain). | CS.arxiv | 2020-09-03 |
| 307 | Evaluation Of Deep Convolutional Generative Adversarial Networks For Data Augmentation Of Chest X-ray Images | SAGAR KORA VENU | In this work, we performed data augmentation on the Chest X-rays dataset through generative modeling (deep convolutional generative adversarial network) which creates artificial instances retaining similar characteristics to the original data and evaluation of the model resulted in Fr\’echet Distance of Inception (FID) score of 1.289. | CS.arxiv | 2020-09-02 |
| 308 | 3D Facial Geometry Recovery From A Depth View With Attention Guided Generative Adversarial Network | XIAOXU CAI et. al. | We present to recover the complete 3D facial geometry from a single depth view by proposing an Attention Guided Generative Adversarial Networks (AGGAN). | CS.arxiv | 2020-09-02 |
| 309 | Adversarially Robust Neural Architectures | MINJING DONG et. al. | This paper thus aims to improve the adversarial robustness of the network from the architecture perspective with NAS framework. | CS.arxiv | 2020-09-02 |
| 310 | Perceptual Deep Neural Networks: Adversarial Robustness Through Input Recreation | DANILO VASCONCELLOS VARGAS et. al. | In this paper, we explore how machines could recreate the input as well as investigate the benefits of such an augmented perception. | CS.arxiv | 2020-09-02 |
| 311 | Open-set Adversarial Defense | RUI SHAO et. al. | In this paper, we show that open-set recognition systems are vulnerable to adversarial attacks. | CS.arxiv | 2020-09-02 |
| 312 | ASTRAL: Adversarial Trained LSTM-CNN For Named Entity Recognition | JIUNIU WANG et. al. | In this paper, we propose an Adversarial Trained LSTM-CNN (ASTRAL) system to improve the current NER method from both the model structure and the training process. | CS.arxiv | 2020-09-02 |
| 313 | MetaSimulator: Simulating Unknown Target Models For Query-Efficient Black-box Attacks | CHEN MA et. al. | In this study, we aim to learn a generalized substitute model called MetaSimulator that can mimic the functionality of the unknown target models. To this end, we build the training data with the form of multi-tasks by collecting query sequences generated in the attack of various existing networks. | CS.arxiv | 2020-09-02 |
| 314 | Adversarial Attacks On Deep Learning Systems For User Identification Based On Motion Sensors | CEZARA BENEGUI et. al. | In this study, we focus on deep learning methods for explicit authentication based on motion sensor signals. | CS.arxiv | 2020-09-02 |
| 315 | Flow-based Detection And Proxy-based Evasion Of Encrypted Malware C2 Traffic | CARLOS NOVO et. al. | In this paper we discuss learning and evasion consequences of the gap between generated and crafted adversarial samples. | CS.arxiv | 2020-09-02 |
| 316 | Deep Generative Model For Image Inpainting With Local Binary Pattern Learning And Spatial Attention | HAIWEI WU et. al. | To tackle this challenge, in this work, we propose a new end-to-end, two-stage (coarse-to-fine) generative model through combining a local binary pattern (LBP) learning network with an actual inpainting network. | CS.arxiv | 2020-09-02 |
| 317 | GIF: Generative Interpretable Faces | PARTHA GHOSH et. al. | On one end of the spectrum, 3D face modeling methods provide parametric control but tend to generate unrealistic images, while on the other end, generative 2D models like GANs (Generative Adversarial Networks) output photo-realistic face images, but lack explicit control. | CS.arxiv | 2020-08-31 |
| 318 | A Mathematical Introduction To Generative Adversarial Nets (GAN) | YANG WANG | The aim of this paper is to give more mathematically oriented students an introduction to GANs in a language that is more familiar to them. | CS.arxiv | 2020-08-31 |
| 319 | A Review Of Single-Source Deep Unsupervised Visual Domain Adaptation | SICHENG ZHAO et. al. | In this paper, we review the latest single-source deep unsupervised domain adaptation methods focused on visual tasks and discuss new perspectives for future research. | CS.arxiv | 2020-08-31 |
| 320 | Shape Defense | ALI BORJI | Two algorithms are proposed, based on the observation that edges are invariant to moderate imperceptible perturbations. | CS.arxiv | 2020-08-30 |
| 321 | An Integrated Approach To Produce Robust Models With High Efficiency | ZHIJIAN LI et. al. | In this work, we try to obtain both features by applying a convergent relaxation quantization algorithm, Binary-Relax (BR), to a robust adversarial-trained model, ResNets Ensemble via Feynman-Kac Formalism (EnResNet). | CS.arxiv | 2020-08-30 |
| 322 | Benchmarking Adversarial Attacks And Defenses For Time-series Data | SHOAIB AHMED SIDDIQUI et. al. | In this paper, we perform detailed benchmarking of well-proven adversarial defense methodologies on time-series data. | CS.arxiv | 2020-08-30 |
| 323 | Zero-Shot Learning From Adversarial Feature Residual To Compact Visual Feature | BO LIU et. al. | Addressing this problem, we propose a novel adversarial network to synthesize compact semantic visual features for ZSL, consisting of a residual generator, a prototype predictor, and a discriminator. | CS.arxiv | 2020-08-29 |
| 324 | Improving Resistance To Adversarial Deformations By Regularizing Gradients | PENGFEI XIA et. al. | In this paper, we focus on adversarial deformations, a typical class of location perturbations, and propose a flow gradient regularization to improve the resistance of models. | CS.arxiv | 2020-08-29 |
| 325 | Adversarial Privacy Preserving Graph Embedding Against Inference Attack | KAIYANG LI et. al. | In this paper, we propose Adversarial Privacy Graph Embedding (APGE), a graph adversarial training framework that integrates the disentangling and purging mechanisms to remove users’ private information from learned node representations. | CS.arxiv | 2020-08-29 |
| 326 | Relational Data Synthesis Using Generative Adversarial Networks: A Design Space Exploration | JU FAN et. al. | We introduce a unified GAN-based framework and define a space of design solutions for each component in the framework, including neural network architectures and training strategies. | CS.arxiv | 2020-08-28 |
| 327 | Adaptive WGAN With Loss Change Rate Balancing | XU OUYANG et. al. | In this paper, we show that this update strategy is not optimal in terms of accuracy and convergence speed, and propose a new update strategy for Wasserstein GANs (WGAN) and other GANs using the WGAN loss(e.g. WGAN-GP, Deblur GAN, and Super-resolution GAN). | CS.arxiv | 2020-08-27 |
| 328 | Minimal Adversarial Examples For Deep Learning On 3D Point Clouds | JAEYEON KIM et. al. | In this work, we explore adversarial attacks for point cloud-based neural networks with a focus on real-world data. | CS.arxiv | 2020-08-27 |
| 329 | Causal Adversarial Network For Learning Conditional And Interventional Distributions | RAHA MORAFFAH et. al. | We propose a generative Causal Adversarial Network (CAN) for learning and sampling from conditional and interventional distributions. | CS.arxiv | 2020-08-26 |
| 330 | An End-to-End Attack On Text-based CAPTCHAs Based On Cycle-Consistent Generative Adversarial Network | CHUNHUI LI et. al. | In this paper, we propose an efficient and simple end-to-end attack method based on cycle-consistent generative adversarial networks. | CS.arxiv | 2020-08-26 |
| 332 | Anime-to-Real Clothing: Cosplay Costume Generation Via Image-to-Image Translation | KOYA TANGO et. al. | To facilitate imagination and reinterpretation from animated images to real garments, this paper presents an automatic costume image generation method based on image-to-image translation. | CS.arxiv | 2020-08-26 |
| 333 | Crossing-Domain Generative Adversarial Networks For Unsupervised Multi-Domain Image-to-Image Translation | XUEWEN YANG et. al. | In this work, we propose a general framework for unsupervised image-to-image translation across multiple domains, which can translate images from domain X to any a domain without requiring direct training between the two domains involved in image translation. | CS.arxiv | 2020-08-26 |
| 334 | Self-Supervised Human Activity Recognition By Augmenting Generative Adversarial Networks | MOHAMMAD ZAKI ZADEH et. al. | This article proposes a novel approach for augmenting generative adversarial network (GAN) with a self-supervised task in order to improve its ability for encoding video representations that are useful in downstream tasks such as human activity recognition. | CS.arxiv | 2020-08-26 |
| 335 | Adversarial Dual Distinct Classifiers For Unsupervised Domain Adaptation | TAOTAO JING et. al. | In this paper, we propose a novel Adversarial Dual Distinct Classifiers Network (AD$^2$CN) to align the source and target domain data distribution simultaneously with matching task-specific category boundaries. | CS.arxiv | 2020-08-26 |
| 336 | Point Adversarial Self Mining: A Simple Method For Facial Expression Recognition In The Wild | PING LIU et. al. | In this paper, the Point Adversarial Self Mining (PASM) approach, a simple yet effective way to progressively mine knowledge from training samples, is proposed to produce training data for CNNs to improve the performance and network generality in Facial Expression Recognition (FER) task. | CS.arxiv | 2020-08-26 |
| 337 | Disentangled Adversarial Autoencoder For Subject-Invariant Physiological Feature Extraction | MO HAN et. al. | To address this issue, we propose an adversarial feature extractor for transfer learning to exploit disentangled universal representations. | CS.arxiv | 2020-08-26 |
| 338 | CnGAN: Generative Adversarial Networks For Cross-network User Preference Generation For Non-overlapped Users | DILRUK PERERA et. al. | As a solution, we propose CnGAN, a novel multi-task learning based, encoder-GAN-recommender architecture. | CS.arxiv | 2020-08-25 |
| 339 | GAN Slimming: All-in-One GAN Compression By A Unified Optimization Framework | HAOTAO WANG et. al. | To this end, we propose the first unified optimization framework combining multiple compression means for GAN compression, dubbed GAN Slimming (GS). | CS.arxiv | 2020-08-25 |
| 340 | An Adversarial Attack Defending System For Securing In-Vehicle Networks | YI LI et. al. | Specifically, we focus on brake-related ECUs in an in-vehicle network. | CS.arxiv | 2020-08-25 |
| 341 | Confidence-aware Adversarial Learning For Self-supervised Semantic Matching | SHUAIYI HUANG et. al. | In this paper, we aim to address the challenging task of semantic matching where matching ambiguity is difficult to resolve even with learned deep features. | CS.arxiv | 2020-08-25 |
| 343 | Two Sides Of The Same Coin: White-box And Black-box Attacks For Transfer Learning | YINGHUA ZHANG et. al. | To systematically measure the effect of both white-box and black-box attacks, we propose a new metric to evaluate how transferable are the adversarial examples produced by a source model to a target model. | CS.arxiv | 2020-08-25 |
| 344 | Likelihood Landscapes: A Unifying Principle Behind Many Adversarial Defenses | FU LIN et. al. | In this work, we investigate the potential effect defense techniques have on the geometry of the likelihood landscape – likelihood of the input images under the trained model. | CS.arxiv | 2020-08-25 |
| 345 | Ptolemy: Architecture Support For Robust Deep Learning | YIMING GAN et. al. | Leveraging this insight, we propose an adversarial sample detection framework, which uses canary paths generated from offline profiling to detect adversarial samples at runtime. | CS.arxiv | 2020-08-23 |
| 346 | Developing And Defeating Adversarial Examples | IAN MCDIARMID-STERLING et. al. | In this work we develop adversarial examples to attack the Yolo V3 object detector [1] and then study strategies to detect and neutralize these examples. | CS.arxiv | 2020-08-23 |
| 347 | Symbolic Semantic Segmentation And Interpretation Of COVID-19 Lung Infections In Chest CT Volumes Based On Emergent Languages | ARITRA CHOWDHURY et. al. | Inspired by human communication of complex ideas through language, we propose a symbolic framework based on emergent languages for the segmentation of COVID-19 infections in CT scans of lungs. | CS.arxiv | 2020-08-22 |
| 348 | Self-Competitive Neural Networks | IMAN SABERI et. al. | In this paper, we generate adversarial samples to refine the Domains of Attraction (DoAs) of each class. In this approach, at each stage, we use the model learned by the primary and generated adversarial data (up to that stage) to manipulate the primary data in a way that look complicated to the DNN. To generate such samples, we pose the problem as an optimization task, where the network weights are fixed and use a gradient descent based method to synthesize adversarial samples that are on the boundary of their true labels and the nearest wrong labels. | CS.arxiv | 2020-08-22 |
| 349 | In-Domain GAN Inversion For Real Image Editing | JIAPENG ZHU et. al. | To solve this problem, we propose an in-domain GAN inversion approach, which not only faithfully reconstructs the input image but also ensures the inverted code to be semantically meaningful for editing. | CS.eccv | 2020-08-21 |
| 350 | Generative Low-bitwidth Data Free Quantization | SHOUKAI XU et. al. | In this paper, we investigate a simple-yet-effective method called Generative Low-bitwidth Data Free Quantization(GDFQ) to remove the data dependence burden. | CS.eccv | 2020-08-21 |
| 351 | MPCC: Matching Priors And Conditionals For Clustering | NICOLÁS ASTORGA et. al. | We propose Matching Priors and Conditionals for Clustering (MPCC), a GAN-based model with an encoder to infer latent variables and cluster categories from data, and a flexible decoder to generate samples from a conditional latent space. | CS.arxiv | 2020-08-21 |
| 352 | AE-OT-GAN: Training GANs From Data Specific Latent Distribution | DONGSHENG AN et. al. | In this paper, we propose the AE-OT-GAN model to utilize the advantages of the both models: generate high quality images and at the same time overcome the mode collapse/mixture problems. | CS.eccv | 2020-08-21 |
| 353 | On Diverse Asynchronous Activity Anticipation | HE ZHAO et. al. | We investigate the joint anticipation of long-term activity labels and their corresponding times with the aim of improving both the naturalness and diversity of predictions. We address these matters using Conditional Adversarial Generative Networks for Discrete Sequences. | CS.eccv | 2020-08-21 |
| 354 | Self-Supervised CycleGAN For Object-Preserving Image-to-Image Domain Adaptation | XINPENG XIE et. al. | In this paper, we propose a novel GAN (namely OP-GAN) to address the problem, which involves a self-supervised module to enforce the image content consistency during image-to-image translations without any extra annotations. | CS.eccv | 2020-08-21 |
| 355 | Semantic Relation Preserving Knowledge Distillation For Image-to-Image Translation | ZEQI LI et. al. | 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. | CS.eccv | 2020-08-21 |
| 356 | Global And Local Enhancement Networks For Paired And Unpaired Image Enhancement | HAN-UL KIM et. al. | A novel approach for paired and unpaired image enhancement is proposed in this work. | CS.eccv | 2020-08-21 |
| 357 | Dual Adversarial Network For Deep Active Learning | SHUO WANG et. al. | In this paper, we investigate the overlapping problem of recent uncertainty-based approaches and propose to alleviate the issue by taking representativeness into consideration. | CS.eccv | 2020-08-21 |
| 358 | GIQA: Generated Image Quality Assessment | SHUYANG GU et. al. | We introduce three GIQA algorithms from two perspectives: learning-based and data-based. | CS.eccv | 2020-08-21 |
| 359 | Off-Policy Reinforcement Learning For Efficient And Effective GAN Architecture Search | YUAN TIAN et. al. | In this paper, we introduce a new reinforcement learning (RL) based neural architecture search (NAS) methodology for effective and efficient generative adversarial network (GAN) architecture search. | CS.eccv | 2020-08-21 |
| 360 | Generate To Adapt: Resolution Adaption Network For Surveillance Face Recognition | HAN FANG et. al. | To avoid this problem, we propose a novel resolution adaption network (RAN) which contains Multi-Resolution Generative Adversarial Networks (MR-GAN) followed by a feature adaption network. | CS.eccv | 2020-08-21 |
| 361 | Learning Disentangled Representations With Latent Variation Predictability | XINQI ZHU et. al. | This paper defines the variation predictability of latent disentangled representations. | CS.eccv | 2020-08-21 |
| 362 | PIPAL: A Large-Scale Image Quality Assessment Dataset For Perceptual Image Restoration | JINJIN GU et. al. | Based on PIPAL, we present new benchmarks for both IQA and super-resolution methods. | CS.eccv | 2020-08-21 |
| 363 | Rewriting A Deep Generative Model | DAVID BAU et. al. | In this paper, we introduce a new problem setting: manipulation of specific rules encoded by a deep generative model. | CS.eccv | 2020-08-21 |
| 364 | CDE-GAN: Cooperative Dual Evolution Based Generative Adversarial Network | SHIMING CHEN et. al. | In this paper, motivated by the cooperative co-evolutionary algorithm, we propose a Cooperative Dual Evolution based Generative Adversarial Network (CDE-GAN) to circumvent these drawbacks. | CS.arxiv | 2020-08-21 |
| 365 | Reconstructing The Noise Variance Manifold For Image Denoising | IOANNIS MARRAS et. al. | To fill the gap, in this work we introduce the idea of a cGAN which explicitly leverages structure in the image noise variance space. | CS.eccv | 2020-08-21 |
| 366 | HardGAN: A Haze-Aware Representation Distillation GAN For Single Image Dehazing | QILI DENG et. al. | In this paper, we present a Haze-Aware Representation Distillation Generative Adversarial Network named HardGAN for single-image dehazing. | CS.eccv | 2020-08-21 |
| 367 | Discriminative Partial Domain Adversarial Network | JIAN HU et. al. | In this paper, a novel Discriminative Partial Domain Adversarial Network (DPDAN) is developed. | CS.eccv | 2020-08-21 |
| 368 | CPGAN: Content-Parsing Generative Adversarial Networks For Text-to-Image Synthesis | JIADONG LIANG et. al. | In this paper we circumvent this problem by focusing on parsing the content of both the input text and the synthesized image thoroughly to model the text-to-image consistency in the semantic level. | CS.eccv | 2020-08-21 |
| 369 | Latent Embedding Feedback And Discriminative Features For Zero-Shot Classification | SANATH NARAYAN et. al. | We propose to enforce semantic consistency at all stages of (generalized) zero-shot learning: training, feature synthesis and classification. | CS.eccv | 2020-08-21 |
| 370 | GANHopper: Multi-Hop GAN For Unsupervised Image-to-Image Translation | WALLACE LIRA et. al. | We introduce GANHopper, an unsupervised image-to-image translation network that transforms images gradually between two domains, through multiple hops. | CS.eccv | 2020-08-21 |
| 371 | Dual Adversarial Network: Toward Real-world Noise Removal And Noise Generation | ZONGSHENG YUE et. al. | In this work, we propose a novel unified framework to simultaneously deal with the noise removal and noise generation tasks. | CS.eccv | 2020-08-21 |
| 372 | XGAIL: Explainable Generative Adversarial Imitation Learning For Explainable Human Decision Analysis | MENGHAI PAN et. al. | This paper addresses this research gap by proposing xGAIL, the first explainable generative adversarial imitation learning framework. | CS.kdd | 2020-08-21 |
| 373 | Domain-Specific Mappings For Generative Adversarial Style Transfer | HSIN-YU CHANG et. al. | For addressing this issue, this paper leverages domain-specific mappings for remapping latent features in the shared content space to domain-specific content spaces. | CS.eccv | 2020-08-21 |
| 374 | XingGAN For Person Image Generation | HAO TANG et. al. | We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person image generation tasks, i.e., translating the pose of a given person to a desired one. | CS.eccv | 2020-08-21 |
| 375 | Learning To Simulate Human Mobility | JIE FENG et. al. | To solve this problem, we propose a model-free generative adversarial framework, which effectively integrates the domain knowledge of human mobility regularity utilized in the model-based methods. | CS.kdd | 2020-08-21 |
| 376 | Improving Movement Predictions Of Traffic Actors In Bird’s-Eye View Models Using GANs And Differentiable Trajectory Rasterization | EASON WANG et. al. | In this paper we build upon these two directions and propose a raster-based conditional GAN architecture, powered by a novel differentiable rasterizer module at the input of the conditional discriminator that maps generated trajectories into the raster space in a differentiable manner. | CS.kdd | 2020-08-21 |
| 377 | Toward Quantifying Ambiguities In Artistic Images | XI WANG et. al. | This paper presents an approach to measuring the perceptual ambiguity of a collection of images. | CS.arxiv | 2020-08-21 |
| 378 | Multimodal Shape Completion Via Conditional Generative Adversarial Networks | RUNDI WU et. al. | Hence, we pose a multi-modal shape completion problem, in which we seek to complete the partial shape with multiple outputs by learning a one-to-many mapping. | CS.eccv | 2020-08-21 |
| 379 | Exploiting Deep Generative Prior For Versatile Image Restoration And Manipulation | XINGANG PAN et. al. | This work presents an effective way to exploit the image prior captured by a generative adversarial network (GAN) trained on large-scale natural images. | CS.eccv | 2020-08-21 |
| 380 | Synthesizing Coupled 3D Face Modalities By Trunk-Branch Generative Adversarial Networks | BARIS GECER et. al. | In this paper, we present the first methodology that generates high-quality texture, shape, and normals jointly, which can be used for photo-realistic synthesis. | CS.eccv | 2020-08-21 |
| 381 | Jointly De-biasing Face Recognition And Demographic Attribute Estimation | SIXUE GONG et. al. | We present a novel de-biasing adversarial network (DebFace) that learns to extract disentangled feature representations for both unbiased face recognition and demographics estimation. | CS.eccv | 2020-08-21 |
| 382 | Lifespan Age Transformation Synthesis | ROY OR-EL et. al. | We propose a new multi domain image-to-image generative adversarial network architecture, whose learned latent space accurately models the continuous aging process in both directions. | CS.eccv | 2020-08-21 |
| 383 | Curb-GAN: Conditional Urban Traffic Estimation Through Spatio-Temporal Generative Adversarial Networks | YINGXUE ZHANG et. al. | To tackle these challenges, we propose a novel Conditional Urban Traffic Generative Adversarial Network (Curb-GAN), which provides traffic estimations in consecutive time slots based on different (unprecedented) travel demands, thus enables urban planners to accurately evaluate urban plans before deploying them. | CS.kdd | 2020-08-21 |
| 384 | MPCC: Matching Priors And Conditionals For Clustering | NICOL&AACUTES ASTORGA et. al. | We propose Matching Priors and Conditionals for Clustering (MPCC), a GAN-based model with an encoder to infer latent variables and cluster categories from data, and a flexible decoder to generate samples from a conditional latent space. | CS.eccv | 2020-08-21 |
| 385 | Multi-level Wavelet-based Generative Adversarial Network For Perceptual Quality Enhancement Of Compressed Video | JIANYI WANG et. al. | In this paper, we focus on enhancing the perceptualquality of compressed video. | CS.eccv | 2020-08-21 |
| 386 | CAFE-GAN: Arbitrary Face Attribute Editing With Complementary Attention Feature | JEONG GI KWAK et. al. | To address this unintended altering problem, we propose a novel GAN model which is designed to edit only the parts of a face pertinent to the target attributes by the concept of Complementary Attention Feature (CAFE). | CS.eccv | 2020-08-21 |
| 387 | Inclusive GAN: Improving Data And Minority Coverage In Generative Models | NING YU et. al. | We develop an extension that allows explicit control over the minority subgroups that the model should ensure to include, and validate its effectiveness at little compromise from the overall performance on the entire dataset. | CS.eccv | 2020-08-21 |
| 388 | OneGAN: Simultaneous Unsupervised Learning Of Conditional Image Generation, Foreground Segmentation, And Fine-Grained Clustering | YANIV BENNY et. al. | We present a method for simultaneously learning, in an unsupervised manner, (i) a conditional image generator, (ii) foreground extraction and segmentation, (iii) clustering into a two-level class hierarchy, and (iv) object removal and background completion, all done without any use of annotation. | CS.eccv | 2020-08-21 |
| 389 | House-GAN: Relational Generative Adversarial Networks For Graph-constrained House Layout Generation | NELSON NAUATA et. al. | This paper proposes a novel graph-constrained generative adversarial network, whose generator and discriminator are built upon relational architecture. | CS.eccv | 2020-08-21 |
| 390 | TopoGAN: A Topology-Aware Generative Adversarial Network | FAN WANG et. al. | In this paper, we propose a novel GAN model that learns the topology of real images, i.e., connectedness and loopy-ness. | CS.eccv | 2020-08-21 |
| 391 | Aligning And Projecting Images To Class-conditional Generative Networks | MINYOUNG HUH et. al. | We present a method for projecting an input image into the space of a class-conditional generative neural network. | CS.eccv | 2020-08-21 |
| 392 | High-Fidelity Synthesis With Disentangled Representation | WONKWANG LEE et. al. | We propose an Information-Distillation Generative Adversarial Network (ID-GAN), a simple yet generic framework that can easily incorporate the existing state-of-the-art models for both disentanglement learning and high-fidelity synthesis. | CS.eccv | 2020-08-21 |
| 393 | SEAL: Learning Heuristics For Community Detection With Generative Adversarial Networks | YAO ZHANG et. al. | In this paper, we instead study the semi-supervised community detection problem where we are given several communities in a network as training data and aim to discover more communities. | CS.kdd | 2020-08-21 |
| 394 | Hallucinating Visual Instances In Total Absentia | JIAYAN QIU et. al. | In this paper, we investigate a new visual restoration task, termed as hallucinating visual instances in total absentia (HVITA). | CS.eccv | 2020-08-21 |
| 395 | Incorporating Reinforced Adversarial Learning In Autoregressive Image Generation | KENAN E. AK et. al. | To address these limitations, we propose to use Reinforced Adversarial Learning (RAL) based on policy gradient optimization for autoregressive models. | CS.eccv | 2020-08-21 |
| 396 | GAN-based Garment Generation Using Sewing Pattern Images | YU SHEN et. al. | We propose a unified method using the generative network. | CS.eccv | 2020-08-21 |
| 397 | TAnoGAN: Time Series Anomaly Detection With Generative Adversarial Networks | MD ABUL BASHAR et. al. | In this paper, we propose a novel GAN-based unsupervised method called TAnoGan for detecting anomalies in time series when a small number of data points are available. | CS.arxiv | 2020-08-21 |
| 398 | Efficient Adversarial Attacks For Visual Object Tracking | SIYUAN LIANG et. al. | We present an end-to-end network FAN (Fast Attack Network) that uses a novel drift loss combined with the embedded feature loss to attack the Siamese network based trackers. | CS.eccv | 2020-08-21 |
| 399 | Vulnerability Vs. Reliability: Disentangled Adversarial Examples For Cross-Modal Learning | CHAO LI et. al. | In this paper, we propose novel Disentangled Adversarial examples for Cross-Modal learning, dubbed DACM. | CS.kdd | 2020-08-21 |
| 400 | Improving Adversarial Robustness By Enforcing Local And Global Compactness | ANH BUI et. al. | In this work, based on an observation from a previous study that the representations of a clean data example and its adversarial examples become more divergent in higher layers of a deep neural net, we propose the Adversary Divergence Reduction Network which enforces local/global compactness and the clustering assumption over an intermediate layer of a deep neural network. | CS.eccv | 2020-08-21 |
| 401 | BIRNAT: Bidirectional Recurrent Neural Networks With Adversarial Training For Video Snapshot Compressive Imaging | ZIHENG CHENG et. al. | We consider the problem of video snapshot compressive imaging (SCI), where multiple high-speed frames are coded by different masks and then summed to a single measurement. | CS.eccv | 2020-08-21 |
| 402 | Adversarial Generative Grammars For Human Activity Prediction | AJ PIERGIOVANNI et. al. | In this paper we propose an adversarial generative grammar model for future prediction. | CS.eccv | 2020-08-21 |
| 403 | AMLN: Adversarial-based Mutual Learning Network For Online Knowledge Distillation | XIAOBING ZHANG et. al. | In this work, we propose an innovative adversarial-based mutual learning network (AMLN) that introduces process-driven learning beyond outcome-driven learning for augmented online knowledge distillation. | CS.eccv | 2020-08-21 |
| 404 | Adversarial Training With Bi-directional Likelihood Regularization For Visual Classification | WEITAO WAN et. al. | We propose that this problem can be solved by explicitly modeling the deep feature distribution, for example as a Gaussian Mixture, and then properly introducing the likelihood regularization into the loss function. | CS.eccv | 2020-08-21 |
| 405 | Bias-based Universal Adversarial Patch Attack For Automatic Check-out | AISHAN LIU et. al. | To address the problem, this paper proposes a bias-based framework to generate class-agnostic universal adversarial patches with strong generalization ability, which exploits both the perceptual and semantic bias of models. | CS.eccv | 2020-08-21 |
| 406 | Attract, Perturb, And Explore: Learning A Feature Alignment Network For Semi-supervised Domain Adaptation | TAEKYUNG KIM et. al. | We propose an SSDA framework that aims to align features via alleviation of the intra-domain discrepancy. | CS.eccv | 2020-08-21 |
| 407 | Connecting The Dots: Detecting Adversarial Perturbations Using Context Inconsistency | SHASHA LI et. al. | In brief, our approach builds a set of autoencoders, one for each object class, appropriately trained so as to output a discrepancy between the input and output if a perturbation was added to the sample and trigger context violation. | CS.eccv | 2020-08-21 |
| 408 | Defense Against Adversarial Attacks Via Controlling Gradient Leaking On Embedded Manifolds | YUERU LI et. al. | In this paper, we present a new perspective, namely gradient leaking hypothesis, to understand the existence of adversarial examples and to further motivate effective defense strategies. | CS.eccv | 2020-08-21 |
| 409 | Interpretable Neural Network Decoupling | YUCHAO LI et. al. | In this paper, we propose a novel architecture decoupling method to interpret the network from a perspective of investigating its calculation paths. | CS.eccv | 2020-08-21 |
| 410 | Progressive Point Cloud Deconvolution Generation Network | LE HUI et. al. | In this paper, we propose an effective point cloud generation method, which can generate multi-resolution point clouds of the same shape from a latent vector. | CS.eccv | 2020-08-21 |
| 411 | Malicious Attacks Against Deep Reinforcement Learning Interpretations | MENGDI HUAI et. al. | Specifically, we introduce the first study of the adversarial attacks against DRL interpretations, and propose an optimization framework based on which the optimal adversarial attack strategy can be derived. | CS.kdd | 2020-08-21 |
| 412 | Interpretability Is A Kind Of Safety: An Interpreter-based Ensemble For Adversary Defense | JINGYUAN WANG et. al. | In light of this, in this paper, we first reveal a gradient-based correlation between sensitivity analysis-based DNN interpreters and the generation process of adversarial examples, which indicates the Achilles’s heel of adversarial attacks and sheds light on linking together the two long-standing challenges of DNN: fragility and unexplainability. We then propose an interpreter-based ensemble framework called X-Ensemble for robust adversary defense. X-Ensemble adopts a novel detection-rectification process and features in building multiple sub-detectors and a rectifier upon various types of interpretation information toward target classifiers. | CS.kdd | 2020-08-21 |
| 413 | HARD-Net: Hardness-AwaRe Discrimination Network For 3D Early Activity Prediction | TIANJIAO LI et. al. | In this paper, we propose a novel Hardness-AwaRe Discrimination Network (HARD-Net) to specifically investigate the relationships between the similar activity pairs that are hard to be discriminated. | CS.eccv | 2020-08-21 |
| 414 | Boosting Decision-based Black-box Adversarial Attacks With Random Sign Flip | WEILUN CHEN et. al. | In this paper, we show that just randomly flipping the signs of a small number of entries in adversarial perturbations can significantly boost the attack performance. | CS.eccv | 2020-08-21 |
| 415 | Robust Tracking Against Adversarial Attacks | SHUAI JIA et. al. | We apply the proposed adversarial attack and defense approaches to state-of-the-art deep tracking algorithms. | CS.eccv | 2020-08-21 |
| 416 | Multitask Learning Strengthens Adversarial Robustness | CHENGZHI MAO et. al. | We present both theoretical and empirical analyses that connect the adversarial robustness of a model to the number of tasks that it is trained on. | CS.eccv | 2020-08-21 |
| 417 | Spatial Attention Pyramid Network For Unsupervised Domain Adaptation | CONGCONG LI et. al. | To that end, in this paper, we design a new spatial attention pyramid network for unsupervised domain adaptation. | CS.eccv | 2020-08-21 |
| 418 | AdvMind: Inferring Adversary Intent Of Black-Box Attacks | REN PANG et. al. | In this paper, we present AdvMind, a new class of estimation models that infer the adversary intent of black-box adversarial attacks in a robust and prompt manner. | CS.kdd | 2020-08-21 |
| 419 | Yet Another Intermediate-Level Attack | QIZHANG LI et. al. | In this paper, we propose a novel method to enhance the black-box transferability of baseline adversarial examples. | CS.eccv | 2020-08-21 |
| 420 | SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking | QING GUO et. al. | In this paper, we identify a new task for the adversarial attack to visual tracking: online generating imperceptible perturbations that mislead trackers along with an incorrect (Untargeted Attack, UA) or specified trajectory (Targeted Attack, TA). | CS.eccv | 2020-08-21 |
| 421 | Adversarial T-shirt! Evading Person Detectors In A Physical World | KAIDI XU et. al. | In this work, we proposed adversarial T-shirts, a robust physical adversarial example for evading person detectors even if it could undergo non-rigid deformation due to a moving person’s pose changes. | CS.eccv | 2020-08-21 |
| 422 | SemanticAdv: Generating Adversarial Examples Via Attribute-conditioned Image Editing | HAONAN QIU et. al. | In this paper, we propose SemanticAdv to generate a new type of semantically realistic adversarial examples via attribute-conditioned image editing. | CS.eccv | 2020-08-21 |
| 423 | Inherent Adversarial Robustness Of Deep Spiking Neural Networks: Effects Of Discrete Input Encoding And Non-Linear Activations | SAIMA SHARMIN et. al. | In this work, we demonstrate that adversarial accuracy of SNNs under gradient-based attacks is higher than their non-spiking counterparts for CIFAR datasets on deep VGG and ResNet architectures, particularly in blackbox attack scenario. | CS.eccv | 2020-08-21 |
| 424 | Sparse Adversarial Attack Via Perturbation Factorization | YANBO FAN et. al. | This work studies the sparse adversarial attack, which aims to generate adversarial perturbations onto partial positions of one benign image, such that the perturbed image is incorrectly predicted by one deep neural network (DNN) model. | CS.eccv | 2020-08-21 |
| 425 | Prior-based Domain Adaptive Object Detection For Hazy And Rainy Conditions | VISHWANATH A. SINDAGI et. al. | To address this issue, we propose an unsupervised prior-based domain adversarial object detection framework for adapting the detectors to hazy and rainy conditions. | CS.eccv | 2020-08-21 |
| 426 | Graph Structure Learning For Robust Graph Neural Networks | WEI JIN et. al. | Therefore, in this paper, we explore these properties to defend adversarial attacks on graphs. | CS.kdd | 2020-08-21 |
| 427 | Improved Adversarial Training Via Learned Optimizer | YUANHAO XIONG et. al. | In this paper, we empirically demonstrate that the commonly used PGD attack may not be optimal for inner maximization, and improved inner optimizer can lead to a more robust model. | CS.eccv | 2020-08-21 |
| 428 | Adversarial Semantic Data Augmentation For Human Pose Estimation | YANRUI BIN et. al. | We instead propose Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity. | CS.eccv | 2020-08-21 |
| 429 | API-Net: Robust Generative Classifier Via A Single Discriminator | XINSHUAI DONG et. al. | This work aims for a solution of generative classifiers that can profit from the merits of both. | CS.eccv | 2020-08-21 |
| 430 | Adversarial Robustness On In- And Out-Distribution Improves Explainability | MAXIMILIAN AUGUSTIN et. al. | In this work we propose RATIO, a training procedure for Robustness via Adversarial Training on In- and Out-distribution, which leads to robust models with reliable and robust confidence estimates on the out-distribution. | CS.eccv | 2020-08-21 |
| 431 | Gabor Layers Enhance Network Robustness | JUAN C. P&EACUTEREZ et. al. | In particular, we explore the effect of replacing the first layers of various deep architectures with Gabor layers (i.e. convolutional layers with filters that are based on learnable Gabor parameters) on robustness against adversarial attacks. | CS.eccv | 2020-08-21 |
| 432 | Adversarial Data Augmentation Via Deformation Statistics | SAHIN OLUT et. al. | To that end, we explore an augmentation strategy which builds statistical deformation models from unlabeled data via principal component analysis and uses the resulting statistical deformation space to augment the labeled training samples. | CS.eccv | 2020-08-21 |
| 433 | Anti-Bandit Neural Architecture Search For Model Defense | HANLIN CHEN et. al. | In this paper, we defend against adversarial attacks using neural architecture search (NAS) which is based on a comprehensive search of denoising blocks, weight-free operations, Gabor filters and convolutions. | CS.eccv | 2020-08-21 |
| 434 | AdvPC: Transferable Adversarial Perturbations On 3D Point Clouds | ABDULLAH HAMDI et. al. | In this work, we present novel data-driven adversarial attacks against 3D point cloud networks. | CS.eccv | 2020-08-21 |
| 435 | Adversarial Ranking Attack And Defense | MO ZHOU et. al. | In this paper, we propose two attacks against deep ranking systems,i.e., Candidate Attack and Query Attack, that can raise or lower the rank of chosen candidates by adversarial perturbations. | CS.eccv | 2020-08-21 |
| 436 | Manifold Projection For Adversarial Defense On Face Recognition | JIANLI ZHOU et. al. | In this paper, we propose Adversarial Variational AutoEncoder (A-VAE), a novel framework to tackle both types of attacks. | CS.eccv | 2020-08-21 |
| 437 | Practical Detection Of Trojan Neural Networks: Data-Limited And Data-Free Cases | REN WANG et. al. | In this paper, we study the problem of the Trojan network (TrojanNet) detection in the data-scarce regime, where only the weights of a trained DNN are accessed by the detector. | CS.eccv | 2020-08-21 |
| 438 | Square Attack: A Query-efficient Black-box Adversarial Attack Via Random Search | MAKSYM ANDRIUSHCHENKO et. al. | We propose the Square Attack, a score-based black-box $l_2$- and $l_\infty$- adversarial attack that does not rely on local gradient information and thus is not affected by gradient masking. | CS.eccv | 2020-08-21 |
| 439 | Adversarial Background-Aware Loss For Weakly-supervised Temporal Activity Localization | KYLE MIN et. al. | Despite recent advances, existing methods for weakly-supervised temporal activity localization struggle to recognize when an activity is not occurring. To address this issue, we propose a novel method named A2CL-PT. | CS.eccv | 2020-08-21 |
| 440 | HGNet: Hybrid Generative Network For Zero-shot Domain Adaptation | HAIFENG XIA et. al. | In this paper, we propose a novel algorithm, Hybrid Generative Network (HGNet) for Zero-shot Domain Adaptation, which embeds an adaptive feature separation (AFS) module into generative architecture. | CS.eccv | 2020-08-21 |
| 441 | Generative Sparse Detection Networks For 3D Single-shot Object Detection | JUNYOUNG GWAK et. al. | To this end, we propose Generative Sparse Detection Network (GSDN), a fully-convolutional single-shot sparse detection network that efficiently generates the support for object proposals. | CS.eccv | 2020-08-21 |
| 442 | Not My Deepfake: Towards Plausible Deniability For Machine-Generated Media | BAIWU ZHANG et. al. | We propose a framework to provide developers of generative models with plausible deniability. | CS.arxiv | 2020-08-20 |
| 443 | Conditional Wasserstein GAN-based Oversampling Of Tabular Data For Imbalanced Learning | JUSTIN ENGELMANN et. al. | Conditional Wasserstein GAN-based Oversampling Of Tabular Data For Imbalanced Learning | CS.arxiv | 2020-08-20 |
| 444 | Towards Adversarial Robustness With 01 Loss Neural Networks | YUNZHE XUE et. al. | Motivated by the general robustness properties of the 01 loss we propose a single hidden layer 01 loss neural network trained with stochastic coordinate descent as a defense against adversarial attacks in machine learning. | CS.arxiv | 2020-08-20 |
| 445 | $β$-Variational Classifiers Under Attack | MARCO MAGGIPINTO et. al. | More in details, we study their robustness and detection capabilities, together with some novel insights on the generative part of the model. | CS.arxiv | 2020-08-20 |
| 446 | Improving Text To Image Generation Using Mode-seeking Function | NAITIK BHISE et. al. | Our aim is to improve the training of the network by using a specialized mode-seeking loss function to avoid this issue. | CS.arxiv | 2020-08-19 |
| 447 | Addressing Neural Network Robustness With Mixup And Targeted Labeling Adversarial Training | ALFRED LAUGROS et. al. | We propose a new data augmentation strategy called M-TLAT and designed to address robustness in a broad sense. | CS.arxiv | 2020-08-19 |
| 448 | Deep Relighting Networks For Image Light Source Manipulation | LI-WEN WANG et. al. | In this paper, we formulate the single image relighting task and propose a novel Deep Relighting Network (DRN) with three parts: 1) scene reconversion, which aims to reveal the primary scene structure through a deep auto-encoder network, 2) shadow prior estimation, to predict light effect from the new light direction through adversarial learning, and 3) re-renderer, to combine the primary structure with the reconstructed shadow view to form the required estimation under the target light source. | CS.arxiv | 2020-08-19 |
| 449 | Unsupervised Cross-domain Image Classification By Distance Metric Guided Feature Alignment | QINGJIE MENG et. al. | To address this problem, we propose distance metric guided feature alignment (MetFA) to extract discriminative as well as domain-invariant features on both source and target domains. | CS.arxiv | 2020-08-19 |
| 450 | Improving Adversarial Robustness Of Deep Neural Networks By Using Semantic Information | LINA WANG et. al. | From this perspective, we propose a method to generate a single but image-agnostic adversarial perturbation that carries the semantic information implying the directions to the fragile parts on the decision boundary and causes inputs to be misclassified as a specified target. | CS.arxiv | 2020-08-18 |
| 451 | Learning From Irregularly-Sampled Time Series: A Missing Data Perspective | STEVEN CHENG-XIAN LI et. al. | In this paper, we consider irregular sampling from the perspective of missing data. | CS.arxiv | 2020-08-17 |
| 452 | Imitation Learning Based On Entropy-regularized Forward And Inverse Reinforcement Learning | EIJI UCHIBE et. al. | This paper proposes Entropy-Regularized Imitation Learning (ERIL), which is a combination of forward and inverse reinforcement learning under the framework of the entropy-regularized Markov decision process. | CS.arxiv | 2020-08-17 |
| 453 | We Learn Better Road Pothole Detection: From Attention Aggregation To Adversarial Domain Adaptation | RUI FAN et. al. | To boost the performance, we propose a novel attention aggregation (AA) framework, which takes the advantages of different types of attention modules. | CS.arxiv | 2020-08-16 |
| 454 | Adversarial Concurrent Training: Optimizing Robustness And Accuracy Trade-off Of Deep Neural Networks | ELAHE ARANI et. al. | To this end, we propose Adversarial Concurrent Training (ACT), which employs adversarial training in a collaborative learning framework whereby we train a robust model in conjunction with a natural model in a minimax game. | CS.arxiv | 2020-08-16 |
| 455 | Attack On Multi-Node Attention For Object Detection | SIZHE CHEN et. al. | This paper focuses on high-transferable adversarial attacks on detection networks, which are crucial for life-concerning systems such as autonomous driving and security surveillance. | CS.arxiv | 2020-08-15 |
| 456 | Evaluating Lossy Compression Rates Of Deep Generative Models | SICONG HUANG et. al. | In this work, we propose to use rate distortion (RD) curves to evaluate and compare deep generative models. | CS.arxiv | 2020-08-15 |
| 457 | CARL: Controllable Agent With Reinforcement Learning For Quadruped Locomotion | YING-SHENG LUO et. al. | In this paper, we present CARL, a quadruped agent that can be controlled with high-level directives and react naturally to dynamic environments. | CS.siggraph | 2020-08-14 |
| 459 | Supervised Topological Maps | FRANCESCO MANNELLA | In this paper we will show how this can be achieved while building a low-dimensional mapping of the input stream, by deriving a generalized algorithm starting from Self Organizing Maps (SOMs). | CS.arxiv | 2020-08-14 |
| 462 | Learned Motion Matching | DANIEL HOLDEN et. al. | In this paper we present a learned alternative to the Motion Matching algorithm which retains the positive properties of Motion Matching but additionally achieves the scalability of neural-network-based generative models. | CS.siggraph | 2020-08-14 |
| 463 | DF-GAN: Deep Fusion Generative Adversarial Networks For Text-to-Image Synthesis | MING TAO et. al. | To solve these limitations, we propose 1) a novel simplified text-to-image backbone which is able to synthesize high-quality images directly by one pair of generator and discriminator, 2) a novel regularization method called Matching-Aware zero-centered Gradient Penalty which promotes the generator to synthesize more realistic and text-image semantic consistent images without introducing extra networks, 3) a novel fusion module called Deep Text-Image Fusion Block which can exploit the semantics of text descriptions effectively and fuse text and image features deeply during the generation process. | CS.arxiv | 2020-08-13 |
| 464 | Recurrent Deconvolutional Generative Adversarial Networks With Application To Text Guided Video Generation | HONGYUAN YU et. al. | This paper proposes a novel model for video generation and especially makes the attempt to deal with the problem of video generation from text descriptions, i.e., synthesizing realistic videos conditioned on given texts. | CS.arxiv | 2020-08-13 |
| 465 | Semantically Adversarial Learnable Filters | ALI SHAHIN SHAMSABADI et. al. | We present the first adversarial framework that crafts perturbations that mislead classifiers by accounting for the content of the images and the semantics of the labels. | CS.arxiv | 2020-08-13 |
| 466 | Adversarial Training And Provable Robustness: A Tale Of Two Objectives | JIAMENG FAN et. al. | We propose a principled framework that combines adversarial training and provable robustness verification for training certifiably robust neural networks. | CS.arxiv | 2020-08-13 |
| 467 | Network Architecture Search For Domain Adaptation | YICHEN LI et. al. | In this paper, we present Neural Architecture Search for Domain Adaptation (NASDA), a principle framework that leverages differentiable neural architecture search to derive the optimal network architecture for domain adaptation task. | CS.arxiv | 2020-08-13 |
| 468 | Weakly Supervised Generative Network For Multiple 3D Human Pose Hypotheses | CHEN LI et. al. | In this paper, we propose a weakly supervised deep generative network to address the inverse problem and circumvent the need for ground truth 2D-to-3D correspondences. | CS.arxiv | 2020-08-13 |
| 469 | Improving The Performance Of Fine-Grain Image Classifiers Via Generative Data Augmentation | SHASHANK MANJUNATH et. al. | To support this method, we developed a novel augmentation method that can manipulate semantically meaningful dimensions (e.g., orientation) of the target object in the embedding space. | CS.arxiv | 2020-08-12 |
| 470 | Mitigating Dataset Imbalance Via Joint Generation And Classification | AADARSH SAHOO et. al. | In this work we address these questions from the perspective of dataset imbalance resulting out of severe under-representation of annotated training data for certain classes and its effect on both deep classification and generation methods. | CS.arxiv | 2020-08-12 |
| 471 | Improving Stability Of LS-GANs For Audio And Speech Signals | MOHAMMAD ESMAEILPOUR et. al. | In this paper we address the instability issue of generative adversarial network (GAN) by proposing a new similarity metric in unitary space of Schur decomposition for 2D representations of audio and speech signals. | CS.arxiv | 2020-08-12 |
| 472 | Feature Binding With Category-Dependant MixUp For Semantic Segmentation And Adversarial Robustness | MD AMIRUL ISLAM et. al. | In this paper, we present a strategy for training convolutional neural networks to effectively resolve interference arising from competing hypotheses relating to inter-categorical information throughout the network. | CS.arxiv | 2020-08-12 |
| 473 | Open Set Recognition With Conditional Probabilistic Generative Models | XIN SUN et. al. | In this paper, we propose a novel framework, called Conditional Probabilistic Generative Models (CPGM), for open set recognition. | CS.arxiv | 2020-08-12 |
| 474 | R-MNet: A Perceptual Adversarial Network For Image Inpainting | JIREH JAM et. al. | We address the problem by proposing a Wasserstein GAN combined with a new reverse mask operator, namely Reverse Masking Network (R-MNet), a perceptual adversarial network for image inpainting. | CS.arxiv | 2020-08-11 |
| 475 | Road Segmentation For Remote Sensing Images Using Adversarial Spatial Pyramid Networks | POURYA SHAMSOLMOALI et. al. | To address these problems, we introduce a new model to apply structured domain adaption for synthetic image generation and road segmentation. | CS.arxiv | 2020-08-10 |
| 476 | T-GD: Transferable GAN-generated Images Detection Framework | HYEONSEONG JEON et. al. | In this work, we present the Transferable GAN-images Detection framework T-GD, a robust transferable framework for an effective detection of GAN-images. | CS.arxiv | 2020-08-10 |
| 477 | Informative Dropout For Robust Representation Learning: A Shape-bias Perspective | BAIFENG SHI et. al. | In this work, we attempt at improving various kinds of robustness universally by alleviating CNN’s texture bias. | CS.arxiv | 2020-08-10 |
| 478 | Adversarial Directed Graph Embedding | SHIJIE ZHU et. al. | In this paper, we propose a novel Directed Graph embedding framework based on Generative Adversarial Network, called DGGAN. | CS.arxiv | 2020-08-09 |
| 479 | Enhancing Robustness Against Adversarial Examples In Network Intrusion Detection Systems | MOHAMMAD J. HASHEMI et. al. | In this paper, we present Reconstruction from Partial Observation (RePO) as a new mechanism to build an NIDS with the help of denoising autoencoders capable of detecting different types of network attacks in a low false alert setting with an enhanced robustness against adversarial example attack. | CS.arxiv | 2020-08-09 |
| 480 | Adversarial Training With Fast Gradient Projection Method Against Synonym Substitution Based Text Attacks | XIAOSEN WANG et. al. | Thereby, we propose a fast text adversarial attack method called Fast Gradient Projection Method (FGPM) based on synonym substitution, which is about 20 times faster than existing text attack methods and could achieve similar attack performance. | CS.arxiv | 2020-08-09 |
| 481 | Multimodal Image-to-Image Translation Via Mutual Information Estimation And Maximization | ZHIWEN ZUO et. al. | In this paper, we present a novel framework that can achieve multimodal image-to-image translation by simply encouraging the statistical dependence between the latent code and the output image in conditional generative adversarial networks. | CS.arxiv | 2020-08-08 |
| 482 | Oversampling Adversarial Network For Class-Imbalanced Fault Diagnosis | MASOUMEH ZAREAPOOR et. al. | We propose a new adversarial network for simultaneous classification and fault detection. | CS.arxiv | 2020-08-07 |
| 483 | Improving The Speed And Quality Of GAN By Adversarial Training | JIACHEN ZHONG et. al. | In this paper, we develop an efficient algorithm, namely FastGAN (Free AdverSarial Training), to improve the speed and quality of GAN training based on the adversarial training technique. | CS.arxiv | 2020-08-07 |
| 484 | Optimizing Information Loss Towards Robust Neural Networks | PHILIP SPERL et. al. | To overcome the downsides of adversarial training while still providing a high level of security, we present a new training approach we call \textit{entropic retraining}. | CS.arxiv | 2020-08-07 |
| 485 | Adversarial Examples On Object Recognition: A Comprehensive Survey | ALEX SERBAN et. al. | In this article we discuss the impact of adversarial examples on security, safety, and robustness of neural networks. | CS.arxiv | 2020-08-07 |
| 486 | Multi-source Heterogeneous Domain Adaptation With Conditional Weighting Adversarial Network | YUAN YAO et. al. | In this paper, we study the multi-source heterogeneous domain adaptation problem, and propose a Conditional Weighting Adversarial Network (CWAN) to address it. | CS.arxiv | 2020-08-06 |
| 487 | Generative Adversarial Networks For Image And Video Synthesis: Algorithms And Applications | MING-YU LIU et. al. | In this paper, we provide an overview of GANs with a special focus on algorithms and applications for visual synthesis. | CS.arxiv | 2020-08-06 |
| 488 | Improve Generalization And Robustness Of Neural Networks Via Weight Scale Shifting Invariant Regularizations | ZIQUAN LIU et. al. | In this paper, we show that a family of regularizers, including weight decay, is ineffective at penalizing the intrinsic norms of weights for networks with positively homogeneous activation functions, such as linear, ReLU and max-pooling functions. | CS.arxiv | 2020-08-06 |
| 489 | Stronger And Faster Wasserstein Adversarial Attacks | KAIWEN WU et. al. | We address this gap in two ways: (a) we develop an exact yet efficient projection operator to enable a stronger projected gradient attack; (b) we show that the Frank-Wolfe method equipped with a suitable linear minimization oracle works extremely fast under Wasserstein constraints. | CS.arxiv | 2020-08-06 |
| 490 | The Emergence Of Adversarial Communication In Multi-Agent Reinforcement Learning | JAN BLUMENKAMP et. al. | In this work, we address this gap by presenting a learning model that accommodates individual non-shared rewards and a differentiable communication channel that is common among all agents. | CS.arxiv | 2020-08-06 |
| 491 | Annealing Genetic GAN For Minority Oversampling | JINGYU HAO et. al. | In this work, we propose an Annealing Genetic GAN (AGGAN) method, which aims to reproduce the distributions closest to the ones of the minority classes using only limited data samples. | CS.arxiv | 2020-08-05 |
| 492 | A Feature-supervised Generative Adversarial Network For Environmental Monitoring During Hazy Days | KE WANG et. al. | Four key technical contributions are made in the paper. | CS.arxiv | 2020-08-05 |
| 493 | GL-GAN: Adaptive Global And Local Bilevel Optimization Model Of Image Generation | YING LIU et. al. | Different from general single global optimization methods, we introduce an adaptive global and local bilevel optimization model(GL-GAN). | CS.arxiv | 2020-08-05 |
| 494 | Robust Deep Reinforcement Learning Through Adversarial Loss | TUOMAS OIKARINEN et. al. | In this paper, we propose RADIAL-RL, a method to train reinforcement learning agents with improved robustness against any $l_p$-bounded adversarial attack. | CS.arxiv | 2020-08-05 |
| 495 | An Imitation From Observation Approach To Sim-to-Real Transfer | SIDDARTH DESAI et. al. | In this paper, we show that a particular grounded sim-to-real approach, grounded action transformation, is closely related to the problem of imitation from observation IfO, learning behaviors that mimic the observations of behavior demonstrations. | CS.arxiv | 2020-08-04 |
| 496 | Learning From A Complementary-label Source Domain: Theory And Algorithms | YIYANG ZHANG et. al. | Thus, in this paper, we propose a novel setting that the source domain is composed of complementary-label data, and a theoretical bound for it is first proved. | CS.arxiv | 2020-08-04 |
| 497 | TOAD-GAN: Coherent Style Level Generation From A Single Example | MAREN AWISZUS et. al. | In this work, we present TOAD-GAN (Token-based One-shot Arbitrary Dimension Generative Adversarial Network), a novel Procedural Content Generation (PCG) algorithm that generates token-based video game levels. | CS.arxiv | 2020-08-04 |
| 498 | Multimodal Image-to-Image Translation Via A Single Generative Adversarial Network | SHIHUA HUANG et. al. | To address this issue, we present a flexible and general SoloGAN model for efficient multimodal I2I translation among multiple domains with unpaired data. | CS.arxiv | 2020-08-04 |
| 499 | Generative Ensemble-Regression: Learning Stochastic Dynamics From Discrete Particle Ensemble Observations | LIU YANG et. al. | We propose a new method for inferring the governing stochastic ordinary differential equations by observing particle ensembles at discrete and sparse time instants, i.e., multiple snapshots. | CS.arxiv | 2020-08-04 |
| 500 | Entropy Guided Adversarial Model For Weakly Supervised Object Localization | SABRINA NARIMENE BENASSOU et. al. | In this present article, we propose to take advantage of the generalization ability of the network and train the model using clean examples and adversarial examples to localize the whole object. | CS.arxiv | 2020-08-04 |
| 501 | TREND: Transferability Based Robust ENsemble Design | DEEPAK RAVIKUMAR et. al. | In this work, we study the effect of network architecture, initialization, input, weight and activation quantization on transferability. | CS.arxiv | 2020-08-04 |
| 502 | Analyzing The Components Of Distributed Coevolutionary GAN Training | JAMAL TOUTOUH et. al. | We investigate the impact on the performance of two algorithm components that influence the diversity during coevolution: the performance-based selection/replacement inside each sub-population and the communication through migration of solutions (networks) among overlapping neighborhoods. | CS.arxiv | 2020-08-03 |
| 503 | C-MI-GAN : Estimation Of Conditional Mutual Information Using MinMax Formulation | ARNAB MONDAL et. al. | In this work, we focus on conditional mutual information (CMI) estimation by utilizing its formulation as a \textit{minmax} optimization problem. | CS.uai | 2020-08-03 |
| 504 | MaskAAE: Latent Space Optimization For Adversarial Auto-Encoders | ARNAB MONDAL et. al. | In this work, we hypothesise that the dimensionality of the AE model’s latent space has a critical effect on the quality of generated data. | CS.uai | 2020-08-03 |
| 505 | Learning Based Methods For Traffic Matrix Estimation From Link Measurements | SHENGHE XU et. al. | In this paper, we consider the TM estimation problem where we have information about the distribution of the demand sizes. | CS.arxiv | 2020-08-03 |
| 506 | Walking On Two Legs: Learning Image Segmentation With Noisy Labels | GUOHUA CHENG et. al. | In this paper, we propose a novel label refinement and sample reweighting method, and a novel generative adversarial network (GAN) is introduced to fuse these two models into an integrated framework. | CS.uai | 2020-08-03 |
| 507 | Robust Collective Classification Against Structural Attacks | KAI ZHOU et. al. | We formulate the task of learning a robust AMN classifier as a bi-level program, where the inner problem is a challenging non- linear integer program that computes optimal structural changes to the AMN. | CS.uai | 2020-08-03 |
| 508 | Probabilistic Safety For Bayesian Neural Networks | MATTHEW WICKER et. al. | We apply our methods to BNNs trained on a regression task, airborne collision avoidance, and MNIST, empirically showing that our approach allows one to certify probabilistic safety of BNNs with millions of parameters. | CS.uai | 2020-08-03 |
| 509 | Batch Norm With Entropic Regularization Turns Deterministic Autoencoders Into Generative Models | AMUR GHOSE et. al. | We show in this work that utilizing batch normalization as a source for non-determinism suffices to turn deterministic autoencoders into generative models on par with variational ones, so long as we add a suitable entropic regularization to the training objective. | CS.uai | 2020-08-03 |
| 510 | Point Cloud Completion By Learning Shape Priors | XIAOGANG WANG et. al. | In view of the difficulty in reconstructing object details in point cloud completion, we propose a shape prior learning method for object completion. | CS.arxiv | 2020-08-02 |
| 511 | Resist : Reconstruction Of Irises From Templates | SOHAIB AHMAD et. al. | We apply RESIST to a traditional Gabor filter pipeline, to a DenseNet (Huang et al., CVPR 2017) feature extractor, and to a DenseNet architecture that works without normalization. | CS.arxiv | 2020-07-31 |
| 512 | Vulnerability Under Adversarial Machine Learning: Bias Or Variance? | HOSSEIN ABOUTALEBI et. al. | In this study, we investigate the effect of adversarial machine learning on the bias and variance of a trained deep neural network and analyze how adversarial perturbations can affect the generalization of a network. | CS.arxiv | 2020-07-31 |
| 513 | TEAM: We Need More Powerful Adversarial Examples For DNNs | YAGUAN QIAN et. al. | In this paper, we propose a novel method (TEAM, Taylor Expansion-Based Adversarial Methods) to generate more powerful adversarial examples than previous methods. | CS.arxiv | 2020-07-31 |
| 514 | Instance Selection For GANs | TERRANCE DEVRIES et. al. | In this work we propose a novel approach to improve sample quality: altering the training dataset via instance selection before model training has taken place. | CS.arxiv | 2020-07-30 |
| 515 | Unsupervised Disentanglement GAN For Domain Adaptive Person Re-Identification | YACINE KHRAIMECHE et. al. | In this paper, we introduce a novel unsupervised disentanglement generative adversarial network (UD-GAN) to address the domain adaptation issue of supervised person ReID. | CS.arxiv | 2020-07-30 |
| 516 | Blending Generative Adversarial Image Synthesis With Rendering For Computer Graphics | EKIM YURTSEVER et. al. | We introduce Hybrid Neural Computer Graphics (HNCG) as an alternative. | CS.arxiv | 2020-07-30 |
| 517 | A Data Augmentation-based Defense Method Against Adversarial Attacks In Neural Networks | YI ZENG et. al. | In this paper, we focus on developing a lightweight defense method that can efficiently invalidate full whitebox adversarial attacks with the compatibility of real-life constraints. | CS.arxiv | 2020-07-30 |
| 518 | Black-box Adversarial Sample Generation Based On Differential Evolution | JUNYU LIN et. al. | In this paper, we propose a black-box technique called Black-box Momentum Iterative Fast Gradient Sign Method (BMI-FGSM) to test the robustness of DNN models. | CS.arxiv | 2020-07-30 |
| 519 | Encoder-Decoder Generative Adversarial Nets For Suffix Generation And Remaining Time Prediction Of Business Process Models | FARBOD TAYMOURI et. al. | This paper proposes an encoder-decoder architecture grounded on Generative Adversarial Networks (GANs), that generates a sequence of activities and their timestamps in an end-to-end way. | CS.arxiv | 2020-07-29 |
| 520 | Translate The Facial Regions You Like Using Region-Wise Normalization | WENSHUANG LIU et. al. | We propose in this paper a region-wise normalization framework, for region level face translation. | CS.arxiv | 2020-07-29 |
| 521 | Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation | YIYANG ZHANG et. al. | To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA). | CS.arxiv | 2020-07-29 |
| 522 | Detecting Anomalous Inputs To DNN Classifiers By Joint Statistical Testing At The Layers | JAYARAM RAGHURAM et. al. | We propose an unsupervised statistical testing framework for detecting such anomalous inputs to a trained DNN classifier based on its internal layer representations. | CS.arxiv | 2020-07-29 |
| 523 | Improving Performance Of Relation Extraction Algorithm Via Leveled Adversarial PCNN And Database Expansion | DIYAH PUSPITANINGRUM | This study introduces database expansion using the Minimum Description Length (MDL) algorithm to expand the database for better relation extraction. | CS.arxiv | 2020-07-29 |
| 524 | Stylized Adversarial Defense | MUZAMMAL NASEER et. al. | Subsequently, we propose a max-margin adversarial training approach that minimizes the distance between source image and its adversary and maximizes the distance between the adversary and the target image. | CS.arxiv | 2020-07-29 |
| 525 | On The Impact Of Lossy Image And Video Compression On The Performance Of Deep Convolutional Neural Network Architectures | MATT POYSER et. al. | Whilst the reported performance of these approaches is impressive, this study investigates the hitherto unapproached question of the impact of commonplace image and video compression techniques on the performance of such deep learning architectures. | CS.arxiv | 2020-07-28 |
| 526 | TrajGAIL: Generating Urban Vehicle Trajectories Using Generative Adversarial Imitation Learning | SEONGJIN CHOI et. al. | Unlike the previous studies that used a discriminative modeling approach, this research suggests a generative modeling approach to learn the underlying distributions of urban vehicle trajectory data. | CS.arxiv | 2020-07-28 |
| 527 | Generative Networks As Inverse Problems With Fractional Wavelet Scattering Networks | JIASONG WU et. al. | In order to further improve the quality of generated images while keep the advantages of GSNs, this paper proposes Generative Fractional Scattering Networks (GFRSNs), which use more expressive fractional wavelet scattering networks (FrScatNets) instead of ScatNets as the encoder to obtain the features (or FrScatNet embeddings) and use the similar CNNs of GSNs as the decoder to generate the image. | CS.arxiv | 2020-07-28 |
| 528 | A Deep Learning Framework For Generation And Analysis Of Driving Scenario Trajectories | ANDREAS DEMETRIOU et. al. | We propose a unified deep learning framework for generation and analysis of driving scenario trajectories, and validate its effectiveness in a principled way. | CS.arxiv | 2020-07-28 |
| 529 | Cassandra: Detecting Trojaned Networks From Adversarial Perturbations | XIAOYU ZHANG et. al. | We propose a method to verify if a pre-trained model is Trojaned or benign. | CS.arxiv | 2020-07-28 |
| 530 | Farsighted Risk Mitigation Of Lateral Movement Using Dynamic Cognitive Honeypots | LINAN HUANG et. al. | In this work, we propose a time-expanded random network to model the stochastic service links in the user-host enterprise network and the adversarial lateral movement. | CS.arxiv | 2020-07-28 |
| 531 | 3DMaterialGAN: Learning 3D Shape Representation From Latent Space For Materials Science Applications | DEVENDRA K. JANGID et. al. | To facilitate novel progress at the intersection of computer vision and materials science, we propose a 3DMaterialGAN network that is capable of recognizing and synthesizing individual grains whose morphology conforms to a given 3D polycrystalline material microstructure. | CS.arxiv | 2020-07-27 |
| 532 | WGANVO: Monocular Visual Odometry Based On Generative Adversarial Networks | JAVIER CREMONA et. al. | In this work we present WGANVO, a Deep Learning based monocular Visual Odometry method. | CS.arxiv | 2020-07-27 |
| 533 | KOVIS: Keypoint-based Visual Servoing With Zero-Shot Sim-to-Real Transfer For Robotics Manipulation | EN YEN PUANG et. al. | We present KOVIS, a novel learning-based, calibration-free visual servoing method for fine robotic manipulation tasks with eye-in-hand stereo camera system. | CS.arxiv | 2020-07-27 |
| 534 | Efficient Generation Of Structured Objects With Constrained Adversarial Networks | LUCA DI LIELLO et. al. | As a remedy, we propose Constrained Adversarial Networks (CANs), an extension of GANs in which the constraints are embedded into the model during training. | CS.arxiv | 2020-07-26 |
| 535 | Towards Purely Unsupervised Disentanglement Of Appearance And Shape For Person Images Generation | HONGTAO YANG et. al. | In this paper, we aim to address this challenge in a more unsupervised manner—we do not require any annotation nor any external task-specific clues. | CS.arxiv | 2020-07-26 |
| 536 | Robust Collective Classification Against Structural Attacks | KAI ZHOU et. al. | Collective learning methods exploit relations among data points to enhance classification performance. | CS.arxiv | 2020-07-26 |
| 537 | Dual Distribution Alignment Network For Generalizable Person Re-Identification | PEIXIAN CHEN et. al. | In this paper, we present a Dual Distribution Alignment Network (DDAN), which handles this challenge by mapping images into a domain-invariant feature space by selectively aligning distributions of multiple source domains. | CS.arxiv | 2020-07-26 |
| 538 | Sequential Recommendation With Self-Attentive Multi-Adversarial Network | RUIYANG REN et. al. | In this paper, we present a Multi-Factor Generative Adversarial Network (MFGAN) for explicitly modeling the effect of context information on sequential recommendation. | CS.sigir | 2020-07-25 |
| 539 | MRGAN: Multi-Rooted 3D Shape Generation With Unsupervised Part Disentanglement | RINON GAL et. al. | We present MRGAN, a multi-rooted adversarial network which generates part-disentangled 3D point-cloud shapes without part-based shape supervision. | CS.arxiv | 2020-07-25 |
| 540 | DVGAN: A Minimax Game For Search Result Diversification Combining Explicit And Implicit Features | JIONGNAN LIU et. al. | To tackle this problem, we propose a supervised diversification framework based on Generative Adversarial Network (GAN). | CS.sigir | 2020-07-25 |
| 541 | ASiNE: Adversarial Signed Network Embedding | YEON-CHANG LEE et. al. | Motivated by a success of generative adversarial networks (GAN) in various domains including information retrieval, we propose a novel signed network embedding framework, ASiNE, which represents each node of a given signed network as a low-dimensional vector based on the adversarial learning. | CS.sigir | 2020-07-25 |
| 542 | Style Is A Distribution Of Features | EDDIE HUANG et. al. | We present a new algorithm for style transfer that fully extracts the style from the features by redefining the style loss as the Wasserstein distance between the distribution of features. | CS.arxiv | 2020-07-25 |
| 543 | Correlated Features Synthesis And Alignment For Zero-shot Cross-modal Retrieval | XING XU et. al. | To address these issues, we propose a novel Correlated Feature Synthesis and Alignment (CFSA) approach to integrate multimodal feature synthesis, common space learning and knowledge transfer for ZS-CMR. | CS.sigir | 2020-07-25 |
| 544 | Generating Images Instead Of Retrieving Them: Relevance Feedback On Generative Adversarial Networks | ANTTI UKKONEN et. al. | Here, we present a methodology for generating images matching the user intention instead of retrieving them. | CS.sigir | 2020-07-25 |
| 545 | MirrorNet: Bio-Inspired Adversarial Attack For Camouflaged Object Segmentation | JINNAN YAN et. al. | In this paper, we propose a novel bio-inspired network, named the MirrorNet, that leverages both instance segmentation and adversarial attack for the camouflaged object segmentation. | CS.arxiv | 2020-07-25 |
| 546 | Generative Attribute Manipulation Scheme For Flexible Fashion Search | XIN YANG et. al. | In this work, we aim to investigate the practical task of flexible fashion search with attribute manipulation, where users can retrieve the target fashion items by replacing the unwanted attributes of an available query image with the desired ones (e.g., changing the collar attribute from v-neck to round). | CS.sigir | 2020-07-25 |
| 547 | Sequential-based Adversarial Optimisation For Personalised Top-N Item Recommendation | JARANA MANOTUMRUKSA et. al. | To address this challenge, we propose a Sequential-based Adversarial Optimisation (SAO) framework that effectively enhances the generalisation of sequential-based factorised approaches. | CS.sigir | 2020-07-25 |
| 548 | Coding Electronic Health Records With Adversarial Reinforcement Path Generation | SHANSHAN WANG et. al. | We propose a coarse-to-fine ICD path generation framework, named Reinforcement Path Generation Network (RPGNet), that implements EHR coding with a Path Generator (PG) and a Path Discriminator (PD). | CS.sigir | 2020-07-25 |
| 549 | Machine-learned Regularization And Polygonization Of Building Segmentation Masks | STEFANO ZORZI et. al. | We propose a machine learning based approach for automatic regularization and polygonization of building segmentation masks. | CS.arxiv | 2020-07-24 |
| 550 | Interpreting Spatially Infinite Generative Models | CHAOCHAO LU et. al. | In this paper we provide a firm theoretical interpretation for infinite spatial generation, by drawing connections to spatial stochastic processes. | CS.arxiv | 2020-07-24 |
| 551 | MADGAN: Unsupervised Medical Anomaly Detection GAN Using Multiple Adjacent Brain MRI Slice Reconstruction | CHANGHEE HAN et. al. | Therefore, we propose unsupervised Medical Anomaly Detection Generative Adversarial Network (MADGAN), a novel two-step method using GAN-based multiple adjacent brain MRI slice reconstruction to detect brain anomalies at different stages on multi-sequence structural MRI: (Reconstruction) Wasserstein loss with Gradient Penalty + 100 L1 loss-trained on 3 healthy brain axial MRI slices to reconstruct the next 3 ones-reconstructs unseen healthy/abnormal scans; (Diagnosis) Average L2 loss per scan discriminates them, comparing the ground truth/reconstructed slices. | CS.arxiv | 2020-07-24 |
| 552 | Artificial Intelligence In The Creative Industries: A Review | NANTHEERA ANANTRASIRICHAI et. al. | This paper reviews the current state of the art in Artificial Intelligence (AI) technologies and applications in the context of the creative industries. | CS.arxiv | 2020-07-24 |
| 553 | Developing Personalized Models Of Blood Pressure Estimation From Wearable Sensors Data Using Minimally-trained Domain Adversarial Neural Networks | LIDA ZHANG et. al. | In this paper, we propose the application of the domain-adversarial training neural network (DANN) method on our multitask learning (MTL) blood pressure estimation model, allowing for knowledge transfer between subjects. | CS.arxiv | 2020-07-24 |
| 554 | Adversarial Mixture Of Experts With Category Hierarchy Soft Constraint | ZHUOJIAN XIAO et. al. | In this work, we leverage the Mixture of Expert (MoE) framework to learn a ranking model that specializes for each query category. | CS.arxiv | 2020-07-24 |
| 555 | Deep Generative Models That Solve PDEs: Distributed Computing For Training Large Data-Free Models | SERGIO BOTELHO et. al. | Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models – training in reasonable time as well as distributing the storage requirements. | CS.arxiv | 2020-07-24 |
| 556 | Optimal Transport Using GANs For Lineage Tracing | NEHA PRASAD et. al. | In this paper, we present Super-OT, a novel approach to computational lineage tracing that combines a supervised learning framework with optimal transport based on Generative Adversarial Networks (GANs). | CS.arxiv | 2020-07-23 |
| 557 | Augmentation Adversarial Training For Unsupervised Speaker Recognition | JAESUNG HUH et. al. | The goal of this work is to train robust speaker recognition models without speaker labels. | CS.arxiv | 2020-07-23 |
| 558 | T-BFA: Targeted Bit-Flip Adversarial Weight Attack | ADNAN SIRAJ RAKIN et. al. | This paper proposes the first work oftargetedBFA based (T-BFA) adversarial weight attack on DNN models, which can intentionally mislead selected inputs to a target output class. | CS.arxiv | 2020-07-23 |
| 559 | Scalable Inference Of Symbolic Adversarial Examples | DIMITAR I. DIMITROV et. al. | We present a novel method for generating symbolic adversarial examples: input regions guaranteed to only contain adversarial examples for the given neural network. | CS.arxiv | 2020-07-23 |
| 560 | Hierarchical Verification For Adversarial Robustness | CONG HAN LIM et. al. | We introduce a new framework for the exact point-wise $\ell_p$ robustness verification problem that exploits the layer-wise geometric structure of deep feed-forward networks with rectified linear activations (ReLU networks). | CS.arxiv | 2020-07-23 |
| 561 | Adversarial Training Reduces Information And Improves Transferability | MATTEO TERZI et. al. | The latter property may seem counter-intuitive as it is widely accepted by the community that classification models should only capture the minimal information (features) required for the task. | CS.arxiv | 2020-07-22 |
| 562 | Real-Time Instrument Segmentation In Robotic Surgery Using Auxiliary Supervised Deep Adversarial Learning | MOBARAKOL ISLAM et. al. | We propose a multi-resolution feature fusion module (MFF) to fuse the feature maps of different dimensions and channels from the auxiliary and main branch. | CS.arxiv | 2020-07-22 |
| 563 | SOCRATES: Towards A Unified Platform For Neural Network Verification | LONG H. PHAM et. al. | In this project, we aim to build a unified framework for developing verification techniques for neural networks. | CS.arxiv | 2020-07-22 |
| 564 | Robust Machine Learning Via Privacy/Rate-Distortion Theory | YE WANG et. al. | Our work draws the connection between optimal robust learning and the privacy-utility tradeoff problem, which is a generalization of the rate-distortion problem. | CS.arxiv | 2020-07-22 |
| 565 | DeepSVG: A Hierarchical Generative Network For Vector Graphics Animation | ALEXANDRE CARLIER et. al. | In this work, we propose a novel hierarchical generative network, called DeepSVG, for complex SVG icons generation and interpolation. | CS.arxiv | 2020-07-22 |
| 566 | AttAN: Attention Adversarial Networks For 3D Point Cloud Semantic Segmentation | GEGE ZHANG et. al. | To address this problem, we first extend adversarial learning to this task and propose a novel framework Attention Adversarial Networks (AttAN). With high-order correlations in label sets learned from the adversarial learning, segmentation network can predict labels closer to the real ones and correct noisy results. | CS.ijcai | 2020-07-21 |
| 567 | Unsupervised Learning Of Solutions To Differential Equations With Generative Adversarial Networks | DYLAN RANDLE et. al. | We present empirical results showing that our method, which we call Differential Equation GAN (DEQGAN), can obtain multiple orders of magnitude lower mean squared errors than an alternative unsupervised neural network method based on (squared) $L_2$, $L_1$, and Huber loss functions. | CS.arxiv | 2020-07-21 |
| 568 | Interpolating GANs To Scaffold Autotelic Creativity | ZIV EPSTEIN et. al. | We present Meet the Ganimals, a casual creator built on interpolations of BigGAN that can generate novel, hybrid animals called ganimals by efficiently searching this possibility space. | CS.arxiv | 2020-07-21 |
| 569 | Latent Regularized Generative Dual Adversarial Network For Abnormal Detection | CHENGWEI CHEN et. al. | Due to the training instability issues existed in previous generative adversarial networks (GANs) based methods, in this paper we propose a dual auxiliary autoencoder to make a tradeoff between the capability of generator and discriminator, leading to a more stable training process and high-quality image reconstruction. | CS.ijcai | 2020-07-21 |
| 570 | Adversarial Mutual Information Learning For Network Embedding | DONGXIAO HE et. al. | To address this problem, we propose to use the adversarial idea on the representation mechanism, i.e. on the encoding mechanism under the framework of autoencoder. | CS.ijcai | 2020-07-21 |
| 571 | Garment Design With Generative Adversarial Networks | CHENXI YUAN et. al. | This paper explores the capabilities of generative adversarial networks (GAN) for automated attribute-level editing of design concepts. | CS.arxiv | 2020-07-21 |
| 572 | Knowledge-Based Regularization In Generative Modeling | NAOYA TAKEISHI et. al. | In this paper, we propose a method to incorporate prior knowledge of feature relations into the learning of general-purpose generative models. | CS.ijcai | 2020-07-21 |
| 573 | Generating Natural Counterfactual Visual Explanations | WENQI ZHAO et. al. | Our research considers changing the attribute description text of class A on the basis of the attributes of class B and generating counterfactual images on the basis of the modified text. | CS.ijcai | 2020-07-21 |
| 574 | Financial Thought Experiment: A GAN-based Approach To Vast Robust Portfolio Selection | CHI SENG PUN et. al. | In this paper, we present a new architecture of GAN and adapt it to portfolio risk minimization problem by adding a regression network to GAN (implementing the second half of the experiment). | CS.ijcai | 2020-07-21 |
| 575 | Super-Resolution And Inpainting With Degraded And Upgraded Generative Adversarial Networks | YAWEN HUANG et. al. | In this paper, we explore the possibility of super-resolving and inpainting images to handle multiple degradations and therefore improve their usability. | CS.ijcai | 2020-07-21 |
| 576 | Triple-GAIL: A Multi-Modal Imitation Learning Framework With Generative Adversarial Nets | CONG FEI et. al. | In this paper, we propose a novel multi-modal GAIL framework, named Triple-GAIL, that is able to learn skill selection and imitation jointly from both expert demonstrations and continuously generated experiences with data augmentation purpose by introducing an auxiliary selector. | CS.ijcai | 2020-07-21 |
| 577 | Inductive Anomaly Detection On Attributed Networks | KAIZE DING et. al. | In this study, we propose to tackle the problem of inductive anomaly detection on attributed networks with a novel unsupervised framework: Aegis (adversarial graph differentiation networks). | CS.ijcai | 2020-07-21 |
| 578 | Towards Accurate And Robust Domain Adaptation Under Noisy Environments | ZHONGYI HAN et. al. | In this paper, we report our attempt towards achieving accurate noise-robust domain adaptation. | CS.ijcai | 2020-07-21 |
| 579 | Recurrent Relational Memory Network For Unsupervised Image Captioning | DAN GUO et. al. | In this paper, we propose a novel memory-based network rather than GAN, named Recurrent Relational Memory Network (R2M). | CS.ijcai | 2020-07-21 |
| 580 | FakeSpotter: A Simple Yet Robust Baseline For Spotting AI-Synthesized Fake Faces | RUN WANG et. al. | In this work, we propose a novel approach, named FakeSpotter, based on monitoring neuron behaviors to spot AI-synthesized fake faces. | CS.ijcai | 2020-07-21 |
| 581 | JANE: Jointly Adversarial Network Embedding | LIANG YANG et. al. | To overcome this vital issue, a novel Joint Adversarial Network Embedding (JANE) framework is proposed to jointly distinguish the real and fake combinations of the embeddings, topology information and node features. | CS.ijcai | 2020-07-21 |
| 582 | Learning Interpretable Representations With Informative Entanglements | EGE BEYAZIT et. al. | In this paper, we propose a new method to enable Generative Adversarial Networks (GANs) to discover salient features that may be entangled in an informative manner, instead of extracting only disentangled features. | CS.ijcai | 2020-07-21 |
| 583 | P-KDGAN: Progressive Knowledge Distillation With GANs For One-class Novelty Detection | ZHIWEI ZHANG et. al. | In this paper, the Generative Adversarial Networks (GANs) based on encoder-decoder-encoder pipeline are used for detection and achieve state-of-the-art performance. | CS.ijcai | 2020-07-21 |
| 584 | Rumor Detection On Social Media With Graph Structured Adversarial Learning | XIAOYU YANG et. al. | Our focus in this work is to develop a robust graph-based detector to identify rumors on social media from an adversarial perspective. | CS.ijcai | 2020-07-21 |
| 585 | Classification With Rejection: Scaling Generative Classifiers With Supervised Deep Infomax | XIN WANG et. al. | In this paper, we propose Supervised Deep InfoMax (SDIM), which introduces supervised probabilistic constraints to the encoder outputs. | CS.ijcai | 2020-07-21 |
| 586 | Stochastic Batch Augmentation With An Effective Distilled Dynamic Soft Label Regularizer | QIAN LI et. al. | In this work, we propose a framework called Stochastic Batch Augmentation (SBA) to address these problems. | CS.ijcai | 2020-07-21 |
| 587 | Fairness-Aware Neural Rényi Minimization For Continuous Features | VINCENT GRARI et. al. | The objective in this paper is to ensure some independence level between the outputs of regression models and any given continuous sensitive variables. | CS.ijcai | 2020-07-21 |
| 588 | Towards Visual Distortion In Black-Box Attacks | NANNAN LI et. al. | In this paper, we propose a novel black-box attack approach that can directly minimize the induced distortion by learning the noise distribution of the adversarial example, assuming only loss-oracle access to the black-box network. | CS.arxiv | 2020-07-21 |
| 589 | Detecting Adversarial Attacks Via Subset Scanning Of Autoencoder Activations And Reconstruction Error | CELIA CINTAS et. al. | We propose an unsupervised method for detecting adversarial attacks in inner layers of autoencoder (AE) networks by maximizing a non-parametric measure of anomalous node activations. | CS.ijcai | 2020-07-21 |
| 590 |