Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging

Fast Adversarial Training (FAT) not only improves the model robustness but also reduces the training cost of standard adversarial training. However, fast adversarial training often suffers from Catastrophic Overfitting (CO), which results in poor robustness performance. Catastrophic Overfitting desc...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Jia, Xiaojun, Chen, Yuefeng, Mao, Xiaofeng, Duan, Ranjie, Gu, Jindong, Zhang, Rong, Xue, Hui, Cao, Xiaochun
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!