A Survey on Interpretability in Visual Recognition

Summary

This paper surveys explainable AI (XAI) for visual recognition models, motivated by deployment in safety-critical areas such as autonomous driving and medical diagnostics. It proposes a multi-dimensional taxonomy based on intent, object, presentation, and methodology, along with evaluation desiderata and metrics, qualitative assessments, and quantitative benchmarks. It also examines the interpretability of Multimodal Large Language Models and practical applications.