Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space

Siwon Kim, Jinoh Oh, Sungjin Lee, Seunghak Yu, Jaeyoung Do, Tara Taghavi; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 10942-10950

Concept-based explanation aims to provide concise and human-understandable explanations of an image classifier. However, existing concept-based explanation methods typically require a significant amount of manually collected concept-annotated images. This is costly and runs the risk of human biases being involved in the explanation. In this paper, we propose counterfactual explanation with text-driven concepts (CounTEX), where the concepts are defined only from text by leveraging a pre-trained multi-modal joint embedding space without additional concept-annotated datasets. A conceptual counterfactual explanation is generated with text-driven concepts. To utilize the text-driven concepts defined in the joint embedding space to interpret target classifier outcome, we present a novel projection scheme for mapping the two spaces with a simple yet effective implementation. We show that CounTEX generates faithful explanations that provide a semantic understanding of model decision rationale robust to human bias.