Published on:
2 May 2024
Primary Category:
Machine Learning
Paper Authors:
Nishad Singhi,
Jae Myung Kim,
Karsten Roth,
Zeynep Akata
Proposes concept intervention realignment module to leverage concept relationships
Finds independent concept treatment reduces intervention efficacy
Realignment module updates related concepts after intervention
Significantly reduces interventions needed for target performance
Easily integrates into existing concept-based models
Improving model performance via concept realignment
This paper proposes a concept intervention realignment module to improve the efficacy of human interventions in concept bottleneck models. It finds that existing approaches often require numerous costly human interventions per image. This is driven by independent treatment of concepts during intervention. To address this, the paper introduces a module to realign concepts based on their relationships, significantly reducing required interventions.
Learning human constraints for assistive robot collaboration
Editing outdated and inappropriate content in text-to-image models
Object detection using interpretable image parts
Entailment modeling for text classification with changing concepts
Learning flexible feature representations improves CTR prediction
Aligning vision-language models with human values
No comments yet, be the first to start the conversation...
Sign up to comment on this paper