We introduce ProtoPool, an interpretable image classification model with a pool of prototypes shared by the classes. The training is more straightforward than in the existing methods because it does not require the pruning stage. It is obtained by introducing a fully differentiable assignment of prototypes to particular classes. Moreover, we introduce a novel focal similarity function to focus the model on the rare foreground features. We show that ProtoPool obtains state-of-the-art accuracy on the CUB-200-2011 and the Stanford Cars datasets, substantially reducing the number of prototypes. We provide a theoretical analysis of the method and a user study to show that our prototypes are more distinctive than those obtained with competitive methods.
@article{arxiv.2112.02902,
title = {Interpretable Image Classification with Differentiable Prototypes Assignment},
author = {Dawid Rymarczyk and Łukasz Struski and Michał Górszczak and Koryna Lewandowska and Jacek Tabor and Bartosz Zieliński},
journal= {arXiv preprint arXiv:2112.02902},
year = {2022}
}