Comprehensive Evaluation of Prototype Neural Networks

Philipp Schlinge, Steffen Meinert, Martin Atzmueller
7/9/2025
cs.LGcs.AI

Official code: uos-sis/quanproto (3 stars, MIT, last commit 2025-09-16).

Abstract

Prototype models are an important method for explainable artificial intelligence (XAI) and interpretable machine learning. In this paper, we perform an in-depth analysis of a set of prominent prototype models including ProtoPNet, ProtoPool and PIPNet. For their assessment, we apply a comprehensive set of metrics. In addition to applying standard metrics from literature, we propose several new metrics to further complement the analysis of model interpretability. In our experimentation, we apply the set of prototype models on a diverse set of datasets including fine-grained classification, Non-IID settings and multi-label classification to further contrast the performance. Furthermore, we also provide our code as an open-source library (https://github.com/uos-sis/quanproto), which facilitates simple application of the metrics itself, as well as extensibility -- providing the option for easily adding new metrics and models.

View on arXivView PDF

Code Implementations(1)

uos-sis/quanprotoOfficial100%
MIT
31Shell, PythonJun 2, 20251 years agoMIT

Similar Papers

On the Interpretability of Part-Prototype Based Classifiers: A Human Centric Analysis

81% match2023

This Looks Better than That: Better Interpretable Models with ProtoPNeXt

80% match2024

Interpretable Prototype-based Graph Information Bottleneck

80% match1 repo212026

Revisiting FunnyBirds evaluation framework for prototypical parts networks

79% match1 repo32024

Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks

79% match2024

Advancing Interpretability in Text Classification through Prototype Learning

79% match2024

Cite this paper

@article{schlinge2025comprehensive,
  title  = {Comprehensive Evaluation of Prototype Neural Networks},
  author = {Philipp Schlinge and Steffen Meinert and Martin Atzmueller},
  year   = {2025},
  eprint = {2507.06819},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.06819v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.06819.svg)](https://codeofpaper.com/paper/2507.06819)

Discussion