A Novel Framework for Automated Explain Vision Model Using Vision-Language Models
This addresses the problem of understanding vision model behavior for researchers and developers to prevent bias and identify trends, though it is incremental as it builds on existing xAI and VLM methods.
The paper tackles the lack of explainability in vision models by proposing a pipeline using Vision-Language Models to explain models at both sample and dataset levels, enabling discovery of failure cases and insights with minimal effort.
The development of many vision models mainly focuses on improving their performance using metrics such as accuracy, IoU, and mAP, with less attention to explainability due to the complexity of applying xAI methods to provide a meaningful explanation of trained models. Although many existing xAI methods aim to explain vision models sample-by-sample, methods explaining the general behavior of vision models, which can only be captured after running on a large dataset, are still underexplored. Furthermore, understanding the behavior of vision models on general images can be very important to prevent biased judgments and help identify the model's trends and patterns. With the application of Vision-Language Models, this paper proposes a pipeline to explain vision models at both the sample and dataset levels. The proposed pipeline can be used to discover failure cases and gain insights into vision models with minimal effort, thereby integrating vision model development with xAI analysis to advance image analysis.