This actually looks like that: Proto-BagNets for local and global interpretability-by-design

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Djoumessi, Kerol, Bah, Bubacarr, Kühlewein, Laura, Berens, Philipp, Koch, Lisa
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909229946765312
author Djoumessi, Kerol
Bah, Bubacarr
Kühlewein, Laura
Berens, Philipp
Koch, Lisa
author_facet Djoumessi, Kerol
Bah, Bubacarr
Kühlewein, Laura
Berens, Philipp
Koch, Lisa
contents Interpretability is a key requirement for the use of machine learning models in high-stakes applications, including medical diagnosis. Explaining black-box models mostly relies on post-hoc methods that do not faithfully reflect the model's behavior. As a remedy, prototype-based networks have been proposed, but their interpretability is limited as they have been shown to provide coarse, unreliable, and imprecise explanations. In this work, we introduce Proto-BagNets, an interpretable-by-design prototype-based model that combines the advantages of bag-of-local feature models and prototype learning to provide meaningful, coherent, and relevant prototypical parts needed for accurate and interpretable image classification tasks. We evaluated the Proto-BagNet for drusen detection on publicly available retinal OCT data. The Proto-BagNet performed comparably to the state-of-the-art interpretable and non-interpretable models while providing faithful, accurate, and clinically meaningful local and global explanations. The code is available at https://github.com/kdjoumessi/Proto-BagNets.
format Preprint
id arxiv_https___arxiv_org_abs_2406_15168
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle This actually looks like that: Proto-BagNets for local and global interpretability-by-design
Djoumessi, Kerol
Bah, Bubacarr
Kühlewein, Laura
Berens, Philipp
Koch, Lisa
Artificial Intelligence
Interpretability is a key requirement for the use of machine learning models in high-stakes applications, including medical diagnosis. Explaining black-box models mostly relies on post-hoc methods that do not faithfully reflect the model's behavior. As a remedy, prototype-based networks have been proposed, but their interpretability is limited as they have been shown to provide coarse, unreliable, and imprecise explanations. In this work, we introduce Proto-BagNets, an interpretable-by-design prototype-based model that combines the advantages of bag-of-local feature models and prototype learning to provide meaningful, coherent, and relevant prototypical parts needed for accurate and interpretable image classification tasks. We evaluated the Proto-BagNet for drusen detection on publicly available retinal OCT data. The Proto-BagNet performed comparably to the state-of-the-art interpretable and non-interpretable models while providing faithful, accurate, and clinically meaningful local and global explanations. The code is available at https://github.com/kdjoumessi/Proto-BagNets.
title This actually looks like that: Proto-BagNets for local and global interpretability-by-design
topic Artificial Intelligence
url https://arxiv.org/abs/2406.15168