تقرير
DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation
العنوان: | DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation |
---|---|
المؤلفون: | Subramanyam, Rakshith, Thopalli, Kowshik, Narayanaswamy, Vivek, Thiagarajan, Jayaraman J. |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
الوصف: | 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/} Comment: Accepted at ECCV (European Conference on Computer Vision) 2024 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2408.00331 |
رقم الأكسشن: | edsarx.2408.00331 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |