The reviewed record of science sign in
Pith

arxiv: 2112.02902 · v2 · pith:266S2OMC · submitted 2021-12-06 · cs.CV · cs.AI· cs.LG

Interpretable Image Classification with Differentiable Prototypes Assignment

Dawid Rymarczyk , {\L}ukasz Struski , Micha{\l} G\'orszczak , Koryna Lewandowska , Jacek Tabor , Bartosz Zieli\'nski This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:266S2OMCrecord.jsonopen to challenge →

classification cs.CV cs.AIcs.LG
keywords prototypesassignmentclassesclassificationdifferentiableimageinterpretableintroduce
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Beyond Points: Spherical Distributional Part Prototypes for Interpretable Classification

    cs.CV 2026-06 unverdicted novelty 6.0

    vMFProto models classes as mixtures of von Mises-Fisher distributions on the sphere, uses OT for assignments, and reports SOTA explanation metrics with competitive accuracy on CUB, Dogs, and Cars using frozen DINO backbones.

  2. Beyond Points: Spherical Distributional Part Prototypes for Interpretable Classification

    cs.CV 2026-06 unverdicted novelty 6.0

    vMFProto models each class as a mixture of von Mises-Fisher components on the hypersphere, learns per-prototype concentrations, and applies entropic OT for assignments, yielding SOTA explanation quality on CUB, Dogs, ...