2 papers
cs.LG2024
Understanding Robust Overfitting from the Feature Generalization Perspective
Chaojian Yu, Xiaolong Shi, Jun Yu +2
Adversarial training (AT) constructs robust neural networks by incorporating adversarial perturbations into natural data. However, it is plagued by the issue of robust overfitting…
cs.CV2024
A Novel Cross-Perturbation for Single Domain Generalization
Dongjia Zhao, Lei Qi, Xiao Shi +2
Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain. However, the limited diversity in the…