Concept Bottleneck Model with Additional Unsupervised Concepts

TL;DR

This paper introduces CBM-AUC, an interpretable AI model combining supervised and unsupervised concepts to improve accuracy and interpretability, especially for large images, outperforming previous models like CBM and SENN.

Contribution

The paper proposes a novel concept bottleneck model that integrates supervised and unsupervised concepts, enhancing interpretability and accuracy with reduced computation.

Findings

CBM-AUC outperforms CBM and SENN in experiments.

Saliency maps align with semantic meanings.

Effective for large-sized images.

Abstract

With the increasing demands for accountability, interpretability is becoming an essential capability for real-world AI applications. However, most methods utilize post-hoc approaches rather than training the interpretable model. In this article, we propose a novel interpretable model based on the concept bottleneck model (CBM). CBM uses concept labels to train an intermediate layer as the additional visible layer. However, because the number of concept labels restricts the dimension of this layer, it is difficult to obtain high accuracy with a small number of labels. To address this issue, we integrate supervised concepts with unsupervised ones trained with self-explaining neural networks (SENNs). By seamlessly training these two types of concepts while reducing the amount of computation, we can obtain both supervised and unsupervised concepts simultaneously, even for large-sized images. We refer to the proposed model as the concept bottleneck model with additional unsupervised concepts (CBM-AUC). We experimentally confirmed that the proposed model outperformed CBM and SENN. We also visualized the saliency map of each concept and confirmed that it was consistent with the semantic meanings.