ECCV 2020 的对抗相关论文（对抗生成、对抗攻击）
点击上方 “ 机器学习与生成对抗网络 ”，关注”星标”
获取有趣、好玩的前沿干货！
戳我，查看GAN的系列专辑~！
本文汇总了ECCV 2020 上部分对抗相关 论文，后续公众号会随缘对一些paper做解读。感兴趣的同学，可先自行根据标题，搜索对应链接（有些paper可能未公布）。值得注意的是，这里的对抗包括了生成对抗GAN 、以及对抗攻击/防御 ，两者 概念上是迥然 的。
House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation
Regularization with Latent Space Virtual Adversarial Training
Model-Agnostic Boundary-Adversarial Sampling for Test-Time Generalization in Few-Shot learning
Multi-task Learning Increases Adversarial Robustness
Towards Automated Testing and Robustification by Semantic Adversarial Data Generation
Adversarial Generative Grammars for Human Activity Prediction
TopoGAN: A Topology-Aware Generative Adversarial Network
Studying the Transferability of Adversarial Attacks on Object DetectorsSpotlight
1915Multimodal Shape Completion via Conditional Generative Adversarial Networks
CPGAN: Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesis
Adversarial T-shirt! Evading Person Detectors in A Physical World
Counterfactual Vision-and-Language Navigation via Adversarial Path Sampler
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition
Improved Adversarial Training via Learned Optimizer
Domain-Specific Mappings for Generative Adversarial Style Transfer
Unpaired Image-to-Image Translation using Adversarial Consistency Loss
Dual Adversarial Network: Toward Real Noise Removal and Noise Generation
Adversarial Continual Learning
Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
AMLN: Adversarial-based Mutual Learning Network for Online Knowledge Distillation
AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds
Bias-based Universal Adversarial Patch Attack for Automatic Check-out
SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing
Symbiotic Adversarial Learning for Attribute-Based Person Search
Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization
Multi-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed Video
Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
Adversarial Ranking Attack and Defense
Boosting Decision-based Black-box Adversarial Attacks with Random Sign Flip
Design and Interpretation of Universal Adversarial Patches in Face Detection
Open-set Adversarial Defense
Robust Tracking against Adversarial Attacks
Semantic Equivalent Adversarial Data Augmentation for Visual Question Answering
Adversarial Semantic Data Augmentation for Human Pose Estimation
Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation
APRICOT: A Dataset of Physical Adversarial Attacks on Object Detection
S parse Adversarial Attack via Perturbation Factorization
Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting
DeepLandscape: Adversarial Modeling of Landscape Videos
Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency
Square Attack: a query-efficient black-box adversarial attack via random search
BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging
Mind the Discriminability: Asymmetric Adversarial Domain Adaptation
Dual Adversarial Network for Deep Active Learning
Adversarial Training with Bi-directional Likelihood Regularization for Visual Classification
Improving Query Efficiency of Black-box Adversarial Attack
Efficient Adversarial Attacks for Visual Object Tracking
Adversarial Robustness on In- and Out-Distribution Improves Explainability
Multi-Source Open-Set Deep Adversarial Domain Adaptation
Improving Adversarial Robustness by Enforcing Local and Global Compactness
TopoGAN: A Generative Adversarial Approach to Topology-Aware Road Segmentation
Discriminative Partial Domain Adversarial Network
Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation
Defense Against Adversarial Attacks via Controlling Gradient Leaking on Embedded Manifolds
Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activations
Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks
Dual Mixup Regularized Learning for Adversarial Domain Adaptation
Adversarial Data Augmentation via Deformation Statistics
Manifold Projection for Adversarial Defense on Face Recognition
猜您喜欢：
超100篇！CVPR 2020最全GAN论文梳理汇总！
拆解组新的GAN：解耦表征MixNMatch
StarGAN第2版：多域多样性图像生成
附下载 | 《可解释的机器学习》中文版
附下载 |《TensorFlow 2.0 深度学习算法实战》
附下载 |《计算机视觉中的数学方法》分享
《基于深度学习的表面缺陷检测方法综述》
《零样本图像分类综述: 十年进展》
《基于深度神经网络的少样本学习综述》
版权声明：本文内容由互联网用户自发贡献，该文观点仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请联系我们举报，一经查实，本站将立刻删除。
发布者：全栈程序员-站长，转载请注明出处：https://javaforall.net/2505.html 原文链接：https://javaforall.net
![Java求最大公约数和最小公倍数[通俗易懂]](https://javaforall.net/wp-content/uploads/2020/11/2020110817443450-480x300.jpg)
