Conference
Aug 2026
Dynamic-Weighted Contrastive Adversarial Training
Adversarial training (AT) is a mainstream paradigm for improving the robustness of deep models. However, natural and adversarial examples often exhibit distributional discrepancies in feature space, and fixed-weight contrastive constraints can conflict with classification learning when applied throughout training. To a...
Jun-Song Zhang, Jian-Wei Zhang, Xiao-Ling Li et al.
· Symposium on Designing Inter... · 0 citations