paper-with-me

Papers

ProtoS-ViT: Visual foundation models for sparse self-explainable classifications

2024-06-14 · Hugues Turbé, Mina Bjelogrlic, Gianmarco Mengaldo, Christian Lovis

Prototypical networks aim to build intrinsically explainable models based on the linear summation of concepts. Concepts are coherent entities that we, as humans, can recognize and associate with a certain object or entity. However, important challenges remain in the fair evaluation of explanation quality provided by these models. This work first proposes an extensive set of quantitative and qualitative metrics which allow to identify drawbacks in current prototypical networks. It then introduces a novel architecture which provides compact explanations, outperforming current prototypical models in terms of explanation quality. Overall, the proposed architecture demonstrates how frozen pre-trained ViT backbones can be effectively turned into prototypical models for both general and domain-specific tasks, in our case biomedical image classifiers. Code is available at \url{https://github.com/hturbe/protosvit}.

📄 PDF Abstract BibTeX arXiv:2406.10025

Code (1)

hturbe/protosvit 공식 구현 pytorch

Tasks

Explainable Models

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

ProtoShotXAI: Using Prototypical Few-Shot Architecture for Explainable AI

2021-10-22 · Samuel Hess, Gregory Ditzler

Unexplainable black-box models create scenarios where anomalies cause deleterious responses, thus creating unacceptable risks. These risks have motivated the field of eXplainable Artificial Intelligence (XAI) to improve …

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)

ProtoSAM: One-Shot Medical Image Segmentation With Foundational Models

2024-07-09 · Lev Ayzenberg, Raja Giryes, Hayit Greenspan

This work introduces a new framework, ProtoSAM, for one-shot medical image segmentation. It combines the use of prototypical networks, known for few-shot segmentation, with SAM - a natural image foundation model. The met…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

ProtoSSL: Interpretable Prototype Learning from Unlabeled Time-Series Data

2026-05-07 · Steven Song, Sahil Sethi, Brett Beaulieu-Jones, Robert L. Grossman arxiv

In time-series domains where both predictive performance and interpretability are essential, deep neural networks achieve strong results but provide limited insight into how their predictions are made. Projection-based p…

Audio Classification

Meta-learners for few-shot weakly-supervised optic disc and cup segmentation on fundus images

2025-12-17 · Pandega Abyan Zumarsyah, Igi Ardiyanto, Hanung Adi Nugroho arxiv

This study develops meta-learners for few-shot weakly-supervised segmentation (FWS) to address the challenge of optic disc (OD) and optic cup (OC) segmentation for glaucoma diagnosis with limited labeled fundus images. W…

Unsupervised Domain Adaptation

From Confusion to Clarity: ProtoScore -- A Framework for Evaluating Prototype-Based XAI

2025-11-11 · Helena Monke, Benjamin Sae-Chew, Benjamin Fresz, Marco F. Huber arxiv

The complexity and opacity of neural networks (NNs) pose significant challenges, particularly in high-stakes fields such as healthcare, finance, and law, where understanding decision-making processes is crucial. To addre…