The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers
This work addresses the problem of evaluating explanation quality in interpretable part-prototype models for researchers in computer vision, but it is incremental as it builds on existing Co-12 properties without introducing new methods.
The paper tackles the lack of comprehensive evaluation methods for interpretable part-prototype image classifiers by reviewing existing work based on the Co-12 properties, revealing research gaps and outlining future approaches to improve explanation quality assessment.
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.