This actually looks like that: Proto-BagNets for local and global interpretability-by-design

TL;DR

Proto-BagNets are a novel interpretable model combining bag-of-local features and prototypes, providing faithful explanations for image classification, demonstrated on retinal OCT data with performance comparable to state-of-the-art models.

Contribution

Introduces Proto-BagNets, a new interpretable-by-design prototype-based model that offers meaningful explanations for image classification tasks.

Findings

Performed well on drusen detection in retinal OCT data.

Provided faithful and clinically meaningful explanations.

Achieved comparable accuracy to state-of-the-art models.

Abstract

Interpretability is a key requirement for the use of machine learning models in high-stakes applications, including medical diagnosis. Explaining black-box models mostly relies on post-hoc methods that do not faithfully reflect the model's behavior. As a remedy, prototype-based networks have been proposed, but their interpretability is limited as they have been shown to provide coarse, unreliable, and imprecise explanations. In this work, we introduce Proto-BagNets, an interpretable-by-design prototype-based model that combines the advantages of bag-of-local feature models and prototype learning to provide meaningful, coherent, and relevant prototypical parts needed for accurate and interpretable image classification tasks. We evaluated the Proto-BagNet for drusen detection on publicly available retinal OCT data. The Proto-BagNet performed comparably to the state-of-the-art interpretable and non-interpretable models while providing faithful, accurate, and clinically meaningful local and global explanations. The code is available at https://github.com/kdjoumessi/Proto-BagNets.