Publications

Detailed Information

Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space

DC Field Value Language
dc.contributor.authorKim, Siwon-
dc.contributor.authorOh, Jinoh-
dc.contributor.authorLee, Sung Jin-
dc.contributor.authorYu, Seung Hak-
dc.contributor.authorDo, Jae Young-
dc.contributor.authorTaghavi, Tara-
dc.date.accessioned2024-05-09T06:42:06Z-
dc.date.available2024-05-09T06:42:06Z-
dc.date.created2023-11-21-
dc.date.issued2023-06-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.10942-10950-
dc.identifier.issn1063-6919-
dc.identifier.urihttps://hdl.handle.net/10371/201360-
dc.description.abstractConcept-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 multimodal 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.-
dc.language영어-
dc.publisherProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titleGrounding Counterfactual Explanation of Image Classifiers to Textual Concept Space-
dc.typeArticle-
dc.identifier.doi10.1109/CVPR52729.2023.01053-
dc.citation.journaltitleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.identifier.wosid001062522103024-
dc.identifier.scopusid2-s2.0-85173920117-
dc.citation.endpage10950-
dc.citation.startpage10942-
dc.description.isOpenAccessN-
dc.contributor.affiliatedAuthorDo, Jae Young-
dc.type.docTypeProceedings Paper-
dc.description.journalClass1-
Appears in Collections:
Files in This Item:
There are no files associated with this item.

Related Researcher

  • College of Engineering
  • Department of Electrical and Computer Engineering
Research Area AI 애플리케이션을 위한 알고리즘-시스템 공동 설계, AI-powered Big Data Management, Generative AI, Large Language Model, ML, 고성능 대규모 AI 데이터 분석 및 처리, 모달 AI

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share