LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909451461591040 |
|---|---|
| author | Bousselham, Walid Boggust, Angie Chaybouti, Sofian Strobelt, Hendrik Kuehne, Hilde |
| author_facet | Bousselham, Walid Boggust, Angie Chaybouti, Sofian Strobelt, Hendrik Kuehne, Hilde |
| contents | Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However, the interpretability of these models remains a challenge. To address this, we propose LeGrad, an explainability method specifically designed for ViTs. LeGrad computes the gradient with respect to the attention maps of ViT layers, considering the gradient itself as the explainability signal. We aggregate the signal over all layers, combining the activations of the last as well as intermediate tokens to produce the merged explainability map. This makes LeGrad a conceptually simple and an easy-to-implement tool for enhancing the transparency of ViTs. We evaluate LeGrad in challenging segmentation, perturbation, and open-vocabulary settings, showcasing its versatility compared to other SotA explainability methods demonstrating its superior spatial fidelity and robustness to perturbations. A demo and the code is available at https://github.com/WalBouss/LeGrad. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_03214 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity Bousselham, Walid Boggust, Angie Chaybouti, Sofian Strobelt, Hendrik Kuehne, Hilde Computer Vision and Pattern Recognition Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However, the interpretability of these models remains a challenge. To address this, we propose LeGrad, an explainability method specifically designed for ViTs. LeGrad computes the gradient with respect to the attention maps of ViT layers, considering the gradient itself as the explainability signal. We aggregate the signal over all layers, combining the activations of the last as well as intermediate tokens to produce the merged explainability map. This makes LeGrad a conceptually simple and an easy-to-implement tool for enhancing the transparency of ViTs. We evaluate LeGrad in challenging segmentation, perturbation, and open-vocabulary settings, showcasing its versatility compared to other SotA explainability methods demonstrating its superior spatial fidelity and robustness to perturbations. A demo and the code is available at https://github.com/WalBouss/LeGrad. |
| title | LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.03214 |