paper-with-me

Papers

ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery

2020-11-29 · Dawid Rymarczyk, Łukasz Struski, Jacek Tabor, Bartosz Zieliński

In this paper, we introduce ProtoPShare, a self-explained method that incorporates the paradigm of prototypical parts to explain its predictions. The main novelty of the ProtoPShare is its ability to efficiently share prototypical parts between the classes thanks to our data-dependent merge-pruning. Moreover, the prototypes are more consistent and the model is more robust to image perturbations than the state of the art method ProtoPNet. We verify our findings on two datasets, the CUB-200-2011 and the Stanford Cars.

📄 PDF Abstract BibTeX arXiv:2011.14340

Code (1)

gmum/ProtoPShare pytorch

Tasks

ClassificationGeneral Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

PIP-Net: Patch-Based Intuitive Prototypes for Interpretable Image Classification

2023-01-01 · CVPR 2023 1 · Meike Nauta, Jörg Schlötterer, Maurice van Keulen, Christin Seifert

Interpretable methods based on prototypical patches recognize various components in an image in order to explain their reasoning to humans. However, existing prototype-based methods can learn prototypes that are not …

Decision Makingimage-classificationImage Classification

One Prototype Is Enough: Single-Prototype Activation for Interpretable Image Classification

2025-06-24 · Yitao Peng, Lianghua He, Die Hu

In this paper, we propose ProtoSolo, a novel deep neural architecture for interpretable image classification inspired by prototypical networks such as ProtoPNet. Existing prototype networks usually rely on the collaborat…

Classificationimage-classificationImage Classification

The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers

2023-07-26 · Meike Nauta, Christin Seifert

Interpretable part-prototype models are computer vision models that are explainable by design. The models learn prototypical parts and recognise these components in an image, thereby combining classification and explanat…

Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability

2025-10-01 · Haifei Zhang, Patrick Barry, Eduardo Brandao arxiv

In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on…

Image Classification

Interpretable Image Classification with Differentiable Prototypes Assignment

2021-12-06 · Dawid Rymarczyk, Łukasz Struski, Michał Górszczak, Koryna Lewandowska 외

We introduce ProtoPool, an interpretable image classification model with a pool of prototypes shared by the classes. The training is more straightforward than in the existing methods because it does not require the pruni…

Classificationimage-classificationImage Classification