Interpretability of Deep Neural Networks using concept-based models offers a promising
way to explain model behavior through human understandable concepts. A parallel line of …

There has been considerable recent interest in interpretable concept-based models such as
Concept Bottleneck Models (CBMs), which first predict human-interpretable concepts and …

Concept Bottleneck Models (CBM) map images to human-interpretable concepts before
making class predictions. Recent approaches automate CBM construction by prompting …

Concept-based explainability methods provide insight into deep learning systems by
constructing explanations using human-understandable concepts. While the literature on …

A problem of incorporating the expert rules into machine learning models for extending the
concept-based learning is formulated in the paper. It is proposed how to combine logical …

Carefully perturbed images, which trick well-generalizing neural networks into high-
confidence misclassifications, have gained considerable attention in recent years. A subfield …

This study marks the inaugural endeavors to amalgamate the concept bottleneck model
(CBM) with knowledge distillation (KD) to cultivate lightweight and interpretable models …

This study presents the first attempt to integrate Concept Bottleneck Model (CBM) with
knowledge distillation (KD) to train lightweight and interpretable models. KD is a promising …