nmndeep/revisiting-at
[NeurIPS 2023] Code for the paper "Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models"
Python
Issues
- 5
imagenet1k and imagenet21k pre-train
#8 opened by xiaoyunxxy - 3
loading a pretrained chekpoint
#7 opened by royg27 - 0
- 4
RobustAcc for L∞=8/255 models.
#5 opened by OUTOFTEN - 4
- 2
- 2
- 2
Different results between Table 1 and 2
#1 opened by youzunzhi