The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers

TL;DR

This paper reviews methods for evaluating the explanation quality of interpretable part-prototype image classifiers, identifies research gaps, and proposes a comprehensive evaluation framework based on the Co-12 properties.

Contribution

It provides a systematic review of evaluation methods for part-prototype models, introduces the Co-12 cheat sheet, and outlines future research directions.

Findings

Identifies gaps in current evaluation practices.

Proposes a comprehensive evaluation framework based on Co-12 properties.

Provides a concise cheat sheet summarizing evaluation criteria.

Abstract

Interpretable part-prototype models are computer vision models that are explainable by design. The models learn prototypical parts and recognise these components in an image, thereby combining classification and explanation. Despite the recent attention for intrinsically interpretable models, there is no comprehensive overview on evaluating the explanation quality of interpretable part-prototype models. Based on the Co-12 properties for explanation quality as introduced in arXiv:2201.08164 (e.g., correctness, completeness, compactness), we review existing work that evaluates part-prototype models, reveal research gaps and outline future approaches for evaluation of the explanation quality of part-prototype models. This paper, therefore, contributes to the progression and maturity of this relatively new research field on interpretable part-prototype models. We additionally provide a ``Co-12 cheat sheet'' that acts as a concise summary of our findings on evaluating part-prototype models.