Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes

TL;DR

Deformable ProtoPNet is an interpretable image classification model that uses spatially flexible prototypes to better handle pose variations, leading to improved accuracy and richer explanations.

Contribution

It introduces spatially deformable prototypes that adapt to input images, enhancing interpretability and accuracy over previous rigid prototype methods.

Findings

Achieves state-of-the-art accuracy among prototype-based models.

Provides more context-rich explanations for classifications.

Effectively captures pose variations and context in images.

Abstract

We present a deformable prototypical part network (Deformable ProtoPNet), an interpretable image classifier that integrates the power of deep learning and the interpretability of case-based reasoning. This model classifies input images by comparing them with prototypes learned during training, yielding explanations in the form of "this looks like that." However, while previous methods use spatially rigid prototypes, we address this shortcoming by proposing spatially flexible prototypes. Each prototype is made up of several prototypical parts that adaptively change their relative spatial positions depending on the input image. Consequently, a Deformable ProtoPNet can explicitly capture pose variations and context, improving both model accuracy and the richness of explanations provided. Compared to other case-based interpretable models using prototypes, our approach achieves state-of-the-art accuracy and gives an explanation with greater context. The code is available at https://github.com/jdonnelly36/Deformable-ProtoPNet.