Concept-based Explanations using Non-negative Concept Activation Vectors and Decision Tree for CNN Models
This work addresses the lack of interpretability in CNNs for computer vision, which is a barrier to deployment in critical industries, though it is incremental as it modifies an existing state-of-the-art method.
The paper tackled the problem of improving interpretability for CNN models by proposing TreeICE, a framework that trains a decision tree on concepts extracted from a concept-based explainer, and found that it outperforms baselines in interpretability and generates more human-readable explanations.
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). The current research direction tends to use extracted features in developing approximation algorithms such as linear or decision tree models to interpret an original model. In this work, we modify one of the state-of-the-art concept-based explanations and propose an alternative framework named TreeICE. We design a systematic evaluation based on the requirements of fidelity (approximate models to original model's labels), performance (approximate models to ground-truth labels), and interpretability (meaningful of approximate models to humans). We conduct computational evaluation (for fidelity and performance) and human subject experiments (for interpretability) We find that Tree-ICE outperforms the baseline in interpretability and generates more human readable explanations in the form of a semantic tree structure. This work features how important to have more understandable explanations when interpretability is crucial.