Title | ||
---|---|---|
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness. |
Abstract | ||
---|---|---|
Adversarial training (AT) for robust representation learning and self-supervised learning (SSL) for unsupervised representation learning are two active research fields. Integrating AT into SSL, multiple prior works have accomplished a highly significant yet challenging task: learning robust representation without labels. A widely used framework is adversarial contrastive learning which couples AT and SSL, and thus constitutes a very complex optimization problem. Inspired by the divide-and-conquer philosophy, we conjecture that it might be simplified as well as improved by solving two sub-problems: non-robust SSL and pseudo-supervised AT. This motivation shifts the focus of the task from seeking an optimal integrating strategy for a coupled problem to finding sub-solutions for sub-problems. With this said, this work discards prior practices of directly introducing AT to SSL frameworks and proposed a two-stage framework termed Decoupled Adversarial Contrastive Learning (DeACL). Extensive experimental results demonstrate that our DeACL achieves SOTA self-supervised adversarial robustness while significantly reducing the training time, which validates its effectiveness and efficiency. Moreover, our DeACL constitutes a more explainable solution, and its success also bridges the gap with semi-supervised AT for exploiting unlabeled samples for robust representation learning. The code is publicly accessible at https://github.com/pantheon5100/DeACL. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1007/978-3-031-20056-4_42 | European Conference on Computer Vision |
Keywords | DocType | Citations |
Adversarial contrastive learning,Adversarial training,Self-supervised learning,Adversarial robustness | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chaoning Zhang | 1 | 2 | 6.82 |
Kang Zhang | 2 | 0 | 0.68 |
Chenshuang Zhang | 3 | 0 | 0.68 |
Axi Niu | 4 | 0 | 0.68 |
Jiu Feng | 5 | 0 | 0.34 |
Chang D. Yoo | 6 | 375 | 45.88 |
In So Kweon | 7 | 2795 | 207.62 |