A Survey on Interpretability in Visual Recognition
Top Cited Papers
- 1 July 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (7) , 8547-8566
Abstract
Visual recognition models have achieved unprecedented success in various tasks. While researchers aim to understand the underlying mechanisms of these models, the growing demand for deployment in safety-critical areas like autonomous driving and medical diagnostics has accelerated the development of eXplainable AI (XAI). Distinct from generic XAI, visual recognition XAI is positioned at the intersection of vision and language, which represent the two most fundamental human modalities and form the cornerstones of multimodal intelligence. This paper provides a systematic survey of XAI in visual recognition by establishing a multi-dimensional taxonomy from a human-centered perspective based on intent, object, presentation, and methodology. Beyond categorization, we summarize critical evaluation desiderata and metrics, conducting an extensive qualitative assessment across different categories and demonstrating quantitative benchmarks within specific dimensions. Furthermore, we explore the interpretability of Multimodal Large Language Models and practical applications, identifying emerging trends and opportunities. By synthesizing these diverse perspectives, this survey provides an insightful roadmap to inspire future research on the interpretability of visual recognition models.Keywords
All Related Versions
Funding Information
- National Key R&D Program of China (2023YFF1105104)
- National Key R&D Program of China (2021ZD0111901)
- National Natural Science Foundation of China (U21B2025)
This publication has 141 references indexed in Scilit:
- DeViL: Decoding Vision features into Language2024
- The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers2023
- Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models2023
- Interpretable Image Classification with Differentiable Prototypes Assignment2022
- Explain to Not Forget: Defending Against Catastrophic Forgetting with XAI2022
- Reframing explanation as an interactive medium: The EQUAS (Explainable QUestion Answering System) projectApplied AI Letters, 2021
- Generating visual explanations with natural languageApplied AI Letters, 2021
- This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition2021
- Grounding Visual Explanations2018
- Interpretable Basis Decomposition for Visual Explanation2018