Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911041777041408 |
|---|---|
| author | Hong, Jung-Ho Kim, Ho-Joong Jeon, Kyu-Sung Lee, Seong-Whan |
| author_facet | Hong, Jung-Ho Kim, Ho-Joong Jeon, Kyu-Sung Lee, Seong-Whan |
| contents | The feature attribution method reveals the contribution of input variables to the decision-making process to provide an attribution map for explanation. Existing methods grounded on the information bottleneck principle compute information in a specific layer to obtain attributions, compressing the features by injecting noise via a parametric damping ratio. However, the attribution obtained in a specific layer neglects evidence of the decision-making process distributed across layers. In this paper, we introduce a comprehensive information bottleneck (CoIBA), which discovers the relevant information in each targeted layer to explain the decision-making process. Our core idea is applying information bottleneck in multiple targeted layers to estimate the comprehensive information by sharing a parametric damping ratio across the layers. Leveraging this shared ratio complements the over-compressed information to discover the omitted clues of the decision by sharing the relevant information across the targeted layers. We suggest the variational approach to fairly reflect the relevant information of each layer by upper bounding layer-wise information. Therefore, CoIBA guarantees that the discarded activation is unnecessary in every targeted layer to make a decision. The extensive experimental results demonstrate the enhancement in faithfulness of the feature attributions provided by CoIBA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04388 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers Hong, Jung-Ho Kim, Ho-Joong Jeon, Kyu-Sung Lee, Seong-Whan Computer Vision and Pattern Recognition The feature attribution method reveals the contribution of input variables to the decision-making process to provide an attribution map for explanation. Existing methods grounded on the information bottleneck principle compute information in a specific layer to obtain attributions, compressing the features by injecting noise via a parametric damping ratio. However, the attribution obtained in a specific layer neglects evidence of the decision-making process distributed across layers. In this paper, we introduce a comprehensive information bottleneck (CoIBA), which discovers the relevant information in each targeted layer to explain the decision-making process. Our core idea is applying information bottleneck in multiple targeted layers to estimate the comprehensive information by sharing a parametric damping ratio across the layers. Leveraging this shared ratio complements the over-compressed information to discover the omitted clues of the decision by sharing the relevant information across the targeted layers. We suggest the variational approach to fairly reflect the relevant information of each layer by upper bounding layer-wise information. Therefore, CoIBA guarantees that the discarded activation is unnecessary in every targeted layer to make a decision. The extensive experimental results demonstrate the enhancement in faithfulness of the feature attributions provided by CoIBA. |
| title | Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.04388 |