1 result found Sort:

hila-chefer
Transformer-Explainability hila-chefer
239
1.8k
mit
21
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
vit bert cvpr2021 bert-model perturbation deep-learning explainability attention-matrix vision-transformer attention-visualization visualize-classifications transformer-interpretability
Created 2020-11-23
86 commits to main branch, last one about a year ago