Publications
Detailed Information
Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Siwon | - |
dc.contributor.author | Oh, Jinoh | - |
dc.contributor.author | Lee, Sung Jin | - |
dc.contributor.author | Yu, Seung Hak | - |
dc.contributor.author | Do, Jae Young | - |
dc.contributor.author | Taghavi, Tara | - |
dc.date.accessioned | 2024-05-09T06:42:06Z | - |
dc.date.available | 2024-05-09T06:42:06Z | - |
dc.date.created | 2023-11-21 | - |
dc.date.issued | 2023-06 | - |
dc.identifier.citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.10942-10950 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | https://hdl.handle.net/10371/201360 | - |
dc.description.abstract | 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 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.language | 영어 | - |
dc.publisher | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.title | Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/CVPR52729.2023.01053 | - |
dc.citation.journaltitle | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.identifier.wosid | 001062522103024 | - |
dc.identifier.scopusid | 2-s2.0-85173920117 | - |
dc.citation.endpage | 10950 | - |
dc.citation.startpage | 10942 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Do, Jae Young | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
- 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
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.