dedeswim/vits-robustness-torch

Code for the paper "A Light Recipe to Train Robust Vision Transformers" [SaTML 2023]

Jupyter Notebook

Issues

Adversarial ImageNet pre-trained weights for DeiT and ConvNexT models.
#2 opened a year ago by HashmatShadab
2
Results for Naturally pretrained models on downstream tasks?
#1 opened 2 years ago by HashmatShadab
1