THAT: Two Head Adversarial Training for Improving Robustness at Scale
Not on the map. Why?
Abstract (arXiv)
Many variants of adversarial training have been proposed, with most research focusing on problems with relatively few classes. In this paper, we propose Two Head Adversarial Training (THAT), a two-stream adversarial learning network that is designed to handle the large-scale many-class ImageNet dataset. The proposed method trains a network with two heads and two loss functions; one to minimize feature-space domain shift between natural and adversarial images, and one to promote high classification accuracy. This combination delivers a hardened network that achieves state of the art robust accuracy while maintaining high natural accuracy on ImageNet. Through extensive experiments, we demonstrate that the proposed framework outperforms alternative methods under both standard and "free" adversarial training settings.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 45 of its 51 references that are in the map. First posted on arXiv 25 Mar 2021.
Builds on
45 of 51 references.
References · 45
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2020End-to-End Object Detection with Transformerscited by 7,384
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
- 2017Non-local Neural Networkscited by 2,290
33 more
- 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
- 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
- 2016Adversarial examples in the physical worldcited by 1,762
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2019Contrastive Multiview Codingcited by 1,297
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
- 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
- 2018Robustness May Be at Odds with Accuracycited by 873
- 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
- 2020Fast is better than free: Revisiting adversarial trainingcited by 723
- 2019Adversarial Training for Free!cited by 638
- 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
- 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
- 2019Adversarial Examples Improve Image Recognitioncited by 283
- 2016Learning Representations for Automatic Colorizationcited by 251
- 2018Generalisation in humans and deep neural networkscited by 237
- 2018Adversarial Logit Pairingcited by 224
- 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 152
- 2019Adversarial Robustness through Local Linearizationcited by 146
- 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
- 2020Adversarial Self-Supervised Contrastive Learningcited by 138
- 2018Are adversarial examples inevitable?cited by 113
- 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
- 2020Contrastive Learning with Adversarial Examplescited by 91
- 2019ClusterFit: Improving Generalization of Visual Representationscited by 82
- 2019Metric Learning for Adversarial Robustnesscited by 77
- 2020Learning Representations by Predicting Bags of Visual Wordscited by 73
- 2019Instance adaptive adversarial training: Improved accuracy tradeoffs in neural netscited by 55
- 2018Evaluating and Understanding the Robustness of Adversarial Logit Pairingcited by 34
- 2019Intriguing properties of adversarial training at scalecited by 33
- 2019Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Searchcited by 19
Built on by
Citing papers per year: 2022: 1.
1 paper.