PuSH - Publication Server of Helmholtz Zentrum München

Singhi, N.* ; Kim, J.M.* ; Roth, K.* ; Akata, Z.

Improving intervention efficacy via concept realignment in concept bottleneck models.

In: (Computer Vision – ECCV 2024). Berlin [u.a.]: Springer, 2025. 422-438 (Lect. Notes Comput. Sc. ; 15084 LNCS)
DOI
Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions as well as human interventions, in which expert users can modify misaligned concept choices to interpretably influence the decision of the model. However, existing approaches often require numerous human interventions per image to achieve strong performances, posing practical challenges in scenarios where obtaining human feedback is expensive. In this paper, we find that this is driven by an independent treatment of concepts during intervention, wherein a change of one concept does not influence the use of other ones. To address this issue, we introduce a trainable concept intervention realignment module, which leverages concept relations to realign concept assignments post-intervention. Across standard benchmarks, we find that concept realignment significantly improves intervention efficacy and reduces the number of interventions needed to reach a target classification performance or concept prediction accuracy. Moreover, it easily integrates into existing concept-based architectures without requiring changes to the models themselves. This reduced cost of human-model collaboration is crucial to enhance the feasibility of CBMs in resource-constrained environments. Our code is available at https://github.com/ExplainableML/concept_realignment.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Conference contribution
Corresponding Author
Keywords Concept Bottlenecks ; Interventions ; Trustworthiness
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Conference Title Computer Vision – ECCV 2024
Journal Lecture Notes in Computer Science
Quellenangaben Volume: 15084 LNCS, Issue: , Pages: 422-438 Article Number: , Supplement: ,
Publisher Springer
Publishing Place Berlin [u.a.]
Non-patent literature Publications
Institute(s) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)