Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Haifei, Barry, Patrick, Brandao, Eduardo
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.00773
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908571804893184
author Zhang, Haifei
Barry, Patrick
Brandao, Eduardo
author_facet Zhang, Haifei
Barry, Patrick
Brandao, Eduardo
contents In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate representations. While CBMs offer a semantically meaningful and interpretable classification pipeline, they often sacrifice predictive performance compared to end-to-end convolutional neural networks. Moreover, the propagation of uncertainty from concept predictions to final label decisions remains underexplored. In this paper, we propose a novel uncertainty-aware and interpretable classifier for the second stage of CBMs. Our method learns a set of binary class-level concept prototypes and uses the distances between predicted concept vectors and each class prototype as both a classification score and a measure of uncertainty. These prototypes also serve as interpretable classification rules, indicating which concepts should be present in an image to justify a specific class prediction. The proposed framework enhances both interpretability and robustness by enabling conformal prediction for uncertain or outlier inputs based on their deviation from the learned binary class-level concept prototypes.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00773
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
Zhang, Haifei
Barry, Patrick
Brandao, Eduardo
Computer Vision and Pattern Recognition
Artificial Intelligence
In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate representations. While CBMs offer a semantically meaningful and interpretable classification pipeline, they often sacrifice predictive performance compared to end-to-end convolutional neural networks. Moreover, the propagation of uncertainty from concept predictions to final label decisions remains underexplored. In this paper, we propose a novel uncertainty-aware and interpretable classifier for the second stage of CBMs. Our method learns a set of binary class-level concept prototypes and uses the distances between predicted concept vectors and each class prototype as both a classification score and a measure of uncertainty. These prototypes also serve as interpretable classification rules, indicating which concepts should be present in an image to justify a specific class prediction. The proposed framework enhances both interpretability and robustness by enabling conformal prediction for uncertain or outlier inputs based on their deviation from the learned binary class-level concept prototypes.
title Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.00773