Authors
Chenyang Zhao, Kun Wang, Janet H Hsiao, Antoni B Chan
Published in
IEEE transactions on pattern analysis and machine intelligence. Volume PP. Jul 17, 2026. Epub Jul 17, 2026.
Abstract
Significant progress has been made in the improvement and downstream applications of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention has been paid to the interpretation of CLIP. We propose a Gradient-based visual and textual Explanation method for CLIP (Grad-ECLIP), which interprets the matching result of CLIP for a specific input image-text pair. By decomposing the encoder's architecture and identifying the relationship between matching similarity and intermediate spatial features, Grad-ECLIP generates effective heat maps that reveal the impact of image regions or words on the CLIP results. Unlike previous Transformer interpretation methods that focus on utilizing self-attention maps, which are typically extremely sparse in CLIP, we produce high-quality visual explanations by applying channel and spatial weights to token features. Qualitative and quantitative evaluations verify the effectiveness and superiority of Grad-ECLIP compared with the state-of-the-art methods. Finally, a series of analyses are conducted based on our visual and textual explanation results, from which we explore the working mechanism of image-text matching, the strengths and limitations in attribution identification of CLIP, and the relationship between the concreteness/abstractness of a word and its usage in CLIP. The code of Grad-ECLIP is available here: https://github.com/Cyang-Zhao/Grad-Eclip.
PMID:
42467585
Bibliographic data and abstract were imported from PubMed on 18 Jul 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 4
- Comments 0