Concept-based Explanations using Non-negative Concept Activation Vectors and Decision Tree for CNN Models

Understand

This paper evaluates whether training a decision tree based on concepts extracted from a concept-based explainer can increase interpretability for Convolutional Neural Networks (CNNs) models and boost the fidelity and performance of the used explainer.

• CNNs for computer vision have shown exceptional performance in critical industries.
• However, it is a significant barrier when deploying CNNs due to their complexity and lack of interpretability.
• Recent studies to explain computer vision models have shifted from extracting low-level features (pixel-based explanations) to mid-or high-level features (concept-based explanations).