paper-with-me

Papers

Interpretable Image Classification with Differentiable Prototypes Assignment

2021-12-06 · Dawid Rymarczyk, Łukasz Struski, Michał Górszczak, Koryna Lewandowska, Jacek Tabor, Bartosz Zieliński

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 pruning stage. It is obtained by introducing a fully differentiable assignment of prototypes to particular classes. Moreover, we introduce a novel focal similarity function to focus the model on the rare foreground features. We show that ProtoPool obtains state-of-the-art accuracy on the CUB-200-2011 and the Stanford Cars datasets, substantially reducing the number of prototypes. We provide a theoretical analysis of the method and a user study to show that our prototypes are more distinctive than those obtained with competitive methods.

📄 PDF Abstract BibTeX arXiv:2112.02902

Code (1)

gmum/protopool 공식 구현 pytorch

Tasks

Classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Representation Learning via Consistent Assignment of Views over Random Partitions

2023-10-19 · NeurIPS 2023 11 · Thalles Silva, Adín Ramírez Rivera

We present Consistent Assignment of Views over Random Partitions (CARP), a self-supervised clustering method for representation learning of visual features. CARP learns prototypes in an end-to-end online fashion using gr…

Copy DetectionImage RetrievalLinear evaluationRepresentation Learning+2

Consistent Assignment for Representation Learning

2021-02-26 · ICLR Workshop EBM 2021 5 · Thalles Santos Silva, Adín Ramírez Rivera

We introduce Consistent Assignment for Representation Learning (CARL). An unsupervised learning method to learn visual representations by combining contrastive learning with deep clustering. By viewing contrastive learn…

ClusteringContrastive LearningDeep ClusteringRepresentation Learning

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

Representation Learning via Consistent Assignment of Views to Clusters

2021-12-31 · Thalles Silva, Adín Ramírez Rivera

We introduce Consistent Assignment for Representation Learning (CARL), an unsupervised learning method to learn visual representations by combining ideas from self-supervised contrastive learning and deep clustering. By …

ClusteringContrastive LearningDeep ClusteringLinear evaluation+2

CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning

2024-12-04 · Runjian Chen, Hang Zhang, Avinash Ravichandran, Wenqi Shao 외

Unsupervised 3D representation learning via masked-and-reconstruction with differentiable rendering is promising to reduce the labeling burden for fusion 3D perception. However, previous literature conduct pre-training f…

GPURepresentation LearningUnsupervised Pre-training