Salvato in:
Dettagli Bibliografici
Autori principali: Schlinge, Philipp, Meinert, Steffen, Atzmueller, Martin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.06819
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911278572765184
author Schlinge, Philipp
Meinert, Steffen
Atzmueller, Martin
author_facet Schlinge, Philipp
Meinert, Steffen
Atzmueller, Martin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06819
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Comprehensive Evaluation of Prototype Neural Networks
Schlinge, Philipp
Meinert, Steffen
Atzmueller, Martin
Machine Learning
Artificial Intelligence
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.
title Comprehensive Evaluation of Prototype Neural Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2507.06819