paper-with-me

Papers

ProtoMask: Segmentation-Guided Prototype Learning

2025-10-01 · Steffen Meinert, Philipp Schlinge, Nils Strodthoff, Martin Atzmueller arxiv

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

📄 PDF Abstract BibTeX arXiv:2510.00683

Code (0)

등록된 구현이 없습니다.

Tasks

Image Segmentation

Similar Papers 제목 키워드 기반

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

2021-04-05 · CVPR 2021 1 · Gen Li, Varun Jampani, Laura Sevilla-Lara, Deqing Sun 외

Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information. However, using one prototype to represent a…

ClusteringFew-Shot Semantic SegmentationSegmentation

Prototype Guided Network for Anomaly Segmentation

2022-01-15 · Yiqing Hao, Yi Jin, Gaoyun An

Semantic segmentation methods can not directly identify abnormal objects in images. Anomaly Segmentation algorithm from this realistic setting can distinguish between in-distribution objects and Out-Of-Distribution (OOD)…

Anomaly SegmentationSegmentationSemantic Segmentation

Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation

2025-07-15 · Shuchang Ye, Usman Naseem, Mingyuan Meng, Jinman Kim

Medical language-guided segmentation, integrating textual clinical reports as auxiliary guidance to enhance image segmentation, has demonstrated significant improvements over unimodal approaches. However, its inherent re…

Image SegmentationSegmentationSemantic Segmentation

Query-guided Prototype Evolution Network for Few-Shot Segmentation

2024-03-11 · Runmin Cong, Hang Xiong, Jinpeng Chen, Wei zhang 외

Previous Few-Shot Segmentation (FSS) approaches exclusively utilize support features for prototype generation, neglecting the specific requirements of the query. To address this, we present the Query-guided Prototype Evo…

Segmentation

SPENet: Self-guided Prototype Enhancement Network for Few-shot Medical Image Segmentation

2025-09-03 · Chao Fan, Xibin Jia, Anqi Xiao, Hongyuan Yu 외 arxiv

Few-Shot Medical Image Segmentation (FSMIS) aims to segment novel classes of medical objects using only a few labeled images. Prototype-based methods have made significant progress in addressing FSMIS. However, they typi…

Medical Image Segmentation