hila-chefer/RobustViT

[NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows to finetune the explainability maps of Vision Transformers to enhance robustness.

语言：Jupyter Notebook · GitHub 星标：134 · Fork：14

话题：explainability · neurips · neurips-2022 · robustness · vision-transformer

在 GitHub 上查看原仓库