Representational Similarity via Interpretable Visual Concepts
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_ | 1866915218352766976 |
|---|---|
| author | Kondapaneni, Neehar Mac Aodha, Oisin Perona, Pietro |
| author_facet | Kondapaneni, Neehar Mac Aodha, Oisin Perona, Pietro |
| contents | How do two deep neural networks differ in how they arrive at a decision? Measuring the similarity of deep networks has been a long-standing open question. Most existing methods provide a single number to measure the similarity of two networks at a given layer, but give no insight into what makes them similar or dissimilar. We introduce an interpretable representational similarity method (RSVC) to compare two networks. We use RSVC to discover shared and unique visual concepts between two models. We show that some aspects of model differences can be attributed to unique concepts discovered by one model that are not well represented in the other. Finally, we conduct extensive evaluation across different vision model architectures and training protocols to demonstrate its effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15699 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Representational Similarity via Interpretable Visual Concepts Kondapaneni, Neehar Mac Aodha, Oisin Perona, Pietro Computer Vision and Pattern Recognition Artificial Intelligence Neurons and Cognition How do two deep neural networks differ in how they arrive at a decision? Measuring the similarity of deep networks has been a long-standing open question. Most existing methods provide a single number to measure the similarity of two networks at a given layer, but give no insight into what makes them similar or dissimilar. We introduce an interpretable representational similarity method (RSVC) to compare two networks. We use RSVC to discover shared and unique visual concepts between two models. We show that some aspects of model differences can be attributed to unique concepts discovered by one model that are not well represented in the other. Finally, we conduct extensive evaluation across different vision model architectures and training protocols to demonstrate its effectiveness. |
| title | Representational Similarity via Interpretable Visual Concepts |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Neurons and Cognition |
| url | https://arxiv.org/abs/2503.15699 |