Saved in:
Bibliographic Details
Main Authors: Meinert, Steffen, Schlinge, Philipp, Strodthoff, Nils, Atzmueller, Martin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.00683
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914070035169280
author Meinert, Steffen
Schlinge, Philipp
Strodthoff, Nils
Atzmueller, Martin
author_facet Meinert, Steffen
Schlinge, Philipp
Strodthoff, Nils
Atzmueller, Martin
contents XAI gained considerable importance in recent years. Methods based on prototypical case-based reasoning have shown a promising improvement in explainability. However, these methods typically rely on additional post-hoc saliency techniques to explain the semantics of learned prototypes. Multiple critiques have been raised about the reliability and quality of such techniques. For this reason, we study the use of prominent image segmentation foundation models to improve the truthfulness of the mapping between embedding and input space. We aim to restrict the computation area of the saliency map to a predefined semantic image patch to reduce the uncertainty of such visualizations. To perceive the information of an entire image, we use the bounding box from each generated segmentation mask to crop the image. Each mask results in an individual input in our novel model architecture named ProtoMask. We conduct experiments on three popular fine-grained classification datasets with a wide set of metrics, providing a detailed overview on explainability characteristics. The comparison with other popular models demonstrates competitive performance and unique explainability features of our model. https://github.com/uos-sis/quanproto
format Preprint
id arxiv_https___arxiv_org_abs_2510_00683
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ProtoMask: Segmentation-Guided Prototype Learning
Meinert, Steffen
Schlinge, Philipp
Strodthoff, Nils
Atzmueller, Martin
Computer Vision and Pattern Recognition
XAI gained considerable importance in recent years. Methods based on prototypical case-based reasoning have shown a promising improvement in explainability. However, these methods typically rely on additional post-hoc saliency techniques to explain the semantics of learned prototypes. Multiple critiques have been raised about the reliability and quality of such techniques. For this reason, we study the use of prominent image segmentation foundation models to improve the truthfulness of the mapping between embedding and input space. We aim to restrict the computation area of the saliency map to a predefined semantic image patch to reduce the uncertainty of such visualizations. To perceive the information of an entire image, we use the bounding box from each generated segmentation mask to crop the image. Each mask results in an individual input in our novel model architecture named ProtoMask. We conduct experiments on three popular fine-grained classification datasets with a wide set of metrics, providing a detailed overview on explainability characteristics. The comparison with other popular models demonstrates competitive performance and unique explainability features of our model. https://github.com/uos-sis/quanproto
title ProtoMask: Segmentation-Guided Prototype Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.00683