Transferring Visual Explainability of Self-Explaining Models to Prediction-Only Models without Additional Training
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_ | 1866908803615686656 |
|---|---|
| author | Yoshikawa, Yuya Shimizu, Ryotaro Kawashima, Takahiro Saito, Yuki |
| author_facet | Yoshikawa, Yuya Shimizu, Ryotaro Kawashima, Takahiro Saito, Yuki |
| contents | In image classification scenarios where both prediction and explanation efficiency are required, self-explaining models that perform both tasks in a single inference are effective. However, for users who already have prediction-only models, training a new self-explaining model from scratch imposes significant costs in terms of both labeling and computation. This study proposes a method to transfer the visual explanation capability of self-explaining models learned in a source domain to prediction-only models in a target domain based on a task arithmetic framework. Our self-explaining model comprises an architecture that extends Vision Transformer-based prediction-only models, enabling the proposed method to endow explanation capability to many trained prediction-only models without additional training. Experiments on various image classification datasets demonstrate that, except for transfers between less-related domains, the transfer of visual explanation capability from source to target domains is successful, and explanation quality in the target domain improves without substantially sacrificing classification accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04380 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Transferring Visual Explainability of Self-Explaining Models to Prediction-Only Models without Additional Training Yoshikawa, Yuya Shimizu, Ryotaro Kawashima, Takahiro Saito, Yuki Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning In image classification scenarios where both prediction and explanation efficiency are required, self-explaining models that perform both tasks in a single inference are effective. However, for users who already have prediction-only models, training a new self-explaining model from scratch imposes significant costs in terms of both labeling and computation. This study proposes a method to transfer the visual explanation capability of self-explaining models learned in a source domain to prediction-only models in a target domain based on a task arithmetic framework. Our self-explaining model comprises an architecture that extends Vision Transformer-based prediction-only models, enabling the proposed method to endow explanation capability to many trained prediction-only models without additional training. Experiments on various image classification datasets demonstrate that, except for transfers between less-related domains, the transfer of visual explanation capability from source to target domains is successful, and explanation quality in the target domain improves without substantially sacrificing classification accuracy. |
| title | Transferring Visual Explainability of Self-Explaining Models to Prediction-Only Models without Additional Training |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2507.04380 |