Abstract | ||
---|---|---|
Aggressive data augmentation is a key component of the strong generalization capabilities of Vision Transformer (ViT). One such data augmentation technique is adversarial training (AT); however, many prior works [28,45] have shown that this often results in poor clean accuracy. In this work, we present pyramid adversarial training (PyramidAT), a simple and effective technique to improve ViT's overall performance. We pair it with a “matched” Dropout and stochastic depth regularization, which adopts the same Dropout and stochastic depth configuration for the clean and adversarial samples. Similar to the improvements on CNNs by AdvProp [61] (not directly applicable to ViT), our pyramid adversarial training breaks the trade-off between in-distribution accuracy and out-of-distribution robustness for ViT and related architectures. It leads to 1.82% absolute improvement on ImageNet clean accuracy for the ViT-B model when trained only on ImageNet-1K data, while simultaneously boosting performance on 7 ImageNet ro-bustness metrics, by absolute numbers ranging from 1.76% to 15.68%. We set a new state-of-the-art for ImageNet-C (41.42 mCE), ImageNet-R (53.92%), and ImageNet-Sketch (41.04%) without extra data, using only the ViT-B/16 backbone and our pyramid adversarial training. Our code is publicly available at pyramidat.github.io. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/CVPR52688.2022.01306 | IEEE Conference on Computer Vision and Pattern Recognition |
Keywords | DocType | Volume |
retrieval,categorization,Deep learning architectures and techniques, Adversarial attack and defense, Machine learning, Recognition: detection | Conference | 2022 |
Issue | Citations | PageRank |
1 | 0 | 0.34 |
References | Authors | |
0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Charles Herrmann | 1 | 0 | 0.34 |
Kyle Sargent | 2 | 0 | 0.34 |
Jiang Lu | 3 | 755 | 37.16 |
Ramin Zabih | 4 | 12976 | 982.19 |
Huiwen Chang | 5 | 26 | 4.73 |
Ce Liu | 6 | 3347 | 188.04 |
Dilip Krishnan | 7 | 0 | 0.34 |
Deqing Sun | 8 | 1061 | 44.84 |