Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP

TL;DR

Grad-ECLIP introduces a gradient-based interpretability method for CLIP, generating visual and textual explanations that reveal how image regions and words influence matching results, enhancing understanding and fine-tuning.

Contribution

It presents a novel gradient-based explanation approach for CLIP that surpasses previous methods by producing high-quality heat maps for interpretability.

Findings

Grad-ECLIP produces effective heat maps for CLIP interpretations.

The method outperforms state-of-the-art explanation techniques.

Analysis reveals insights into CLIP's working mechanism and limitations.

Abstract

Significant progress has been achieved on the improvement and downstream usages of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention is 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 specific input image-text pair. By decomposing the architecture of the encoder and discovering the relationship between the matching similarity and intermediate spatial features, Grad-ECLIP produces effective heat maps that show the influence of image regions or words on the CLIP results. Different from the previous Transformer interpretation methods that focus on the utilization of self-attention maps, which are typically extremely sparse in CLIP, we produce high-quality visual explanations by applying channel and spatial weights on token features. Qualitative and quantitative evaluations verify the effectiveness and superiority of Grad-ECLIP compared with the state-of-the-art methods. Furthermore, a series of analysis 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. Finally, based on the ability of explanation map that indicates text-specific saliency region of input image, we also propose an application with Grad-ECLIP, which is adopted to boost the fine-grained alignment in the CLIP fine-tuning. The code of Grad-ECLIP is available here: https://github.com/Cyang-Zhao/Grad-Eclip.