DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916342405267456 |
|---|---|
| author | Subramanyam, Rakshith Thopalli, Kowshik Narayanaswamy, Vivek Thiagarajan, Jayaraman J. |
| author_facet | Subramanyam, Rakshith Thopalli, Kowshik Narayanaswamy, Vivek Thiagarajan, Jayaraman J. |
| contents | Reliably detecting when a deployed machine learning model is likely to fail on a given input is crucial for ensuring safe operation. In this work, we propose DECIDER (Debiasing Classifiers to Identify Errors Reliably), a novel approach that leverages priors from large language models (LLMs) and vision-language models (VLMs) to detect failures in image classification models. DECIDER utilizes LLMs to specify task-relevant core attributes and constructs a ``debiased'' version of the classifier by aligning its visual features to these core attributes using a VLM, and detects potential failure by measuring disagreement between the original and debiased models. In addition to proactively identifying samples on which the model would fail, DECIDER also provides human-interpretable explanations for failure through a novel attribute-ablation strategy. Through extensive experiments across diverse benchmarks spanning subpopulation shifts (spurious correlations, class imbalance) and covariate shifts (synthetic corruptions, domain shifts), DECIDER consistently achieves state-of-the-art failure detection performance, significantly outperforming baselines in terms of the overall Matthews correlation coefficient as well as failure and success recall. Our codes can be accessed at~\url{https://github.com/kowshikthopalli/DECIDER/} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00331 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation Subramanyam, Rakshith Thopalli, Kowshik Narayanaswamy, Vivek Thiagarajan, Jayaraman J. Computer Vision and Pattern Recognition Reliably detecting when a deployed machine learning model is likely to fail on a given input is crucial for ensuring safe operation. In this work, we propose DECIDER (Debiasing Classifiers to Identify Errors Reliably), a novel approach that leverages priors from large language models (LLMs) and vision-language models (VLMs) to detect failures in image classification models. DECIDER utilizes LLMs to specify task-relevant core attributes and constructs a ``debiased'' version of the classifier by aligning its visual features to these core attributes using a VLM, and detects potential failure by measuring disagreement between the original and debiased models. In addition to proactively identifying samples on which the model would fail, DECIDER also provides human-interpretable explanations for failure through a novel attribute-ablation strategy. Through extensive experiments across diverse benchmarks spanning subpopulation shifts (spurious correlations, class imbalance) and covariate shifts (synthetic corruptions, domain shifts), DECIDER consistently achieves state-of-the-art failure detection performance, significantly outperforming baselines in terms of the overall Matthews correlation coefficient as well as failure and success recall. Our codes can be accessed at~\url{https://github.com/kowshikthopalli/DECIDER/} |
| title | DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.00331 |