Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910349980073984 |
|---|---|
| author | Jiang, Chaoquan Wang, Jinqiang Hu, Rui Sang, Jitao |
| author_facet | Jiang, Chaoquan Wang, Jinqiang Hu, Rui Sang, Jitao |
| contents | Vision models with high overall accuracy often exhibit systematic errors in specific scenarios, posing potential serious safety concerns. Diagnosing bugs of vision models is gaining increased attention, however traditional diagnostic approaches require annotation efforts (eg rich metadata accompanying each samples of CelebA). To address this issue,We propose a language-assisted diagnostic method that uses texts instead of images to diagnose bugs in vision models based on multi-modal models (eg CLIP). Our approach connects the embedding space of CLIP with the buggy vision model to be diagnosed; meanwhile, utilizing a shared classifier and the cross-modal transferability of embedding space from CLIP, the text-branch of CLIP become a proxy model to find bugs in the buggy model. The proxy model can classify texts paired with images. During the diagnosis, a Large Language Model (LLM) is employed to obtain task-relevant corpora, and this corpora is used to extract keywords. Descriptions constructed with templates containing these keywords serve as input text to probe errors in the proxy model. Finally, we validate the ability to diagnose existing visual models using language on the Waterbirds and CelebA datasets, we can identify bugs comprehensible to human experts, uncovering not only known bugs but also previously unknown ones. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_05588 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs Jiang, Chaoquan Wang, Jinqiang Hu, Rui Sang, Jitao Artificial Intelligence Computer Vision and Pattern Recognition Vision models with high overall accuracy often exhibit systematic errors in specific scenarios, posing potential serious safety concerns. Diagnosing bugs of vision models is gaining increased attention, however traditional diagnostic approaches require annotation efforts (eg rich metadata accompanying each samples of CelebA). To address this issue,We propose a language-assisted diagnostic method that uses texts instead of images to diagnose bugs in vision models based on multi-modal models (eg CLIP). Our approach connects the embedding space of CLIP with the buggy vision model to be diagnosed; meanwhile, utilizing a shared classifier and the cross-modal transferability of embedding space from CLIP, the text-branch of CLIP become a proxy model to find bugs in the buggy model. The proxy model can classify texts paired with images. During the diagnosis, a Large Language Model (LLM) is employed to obtain task-relevant corpora, and this corpora is used to extract keywords. Descriptions constructed with templates containing these keywords serve as input text to probe errors in the proxy model. Finally, we validate the ability to diagnose existing visual models using language on the Waterbirds and CelebA datasets, we can identify bugs comprehensible to human experts, uncovering not only known bugs but also previously unknown ones. |
| title | Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.05588 |