Contrastive prototype learning with semantic patchmix for few-shot image classification

doi:10.1016/j.engappai.2024.109917

Contrastive prototype learning with semantic patchmix for few-shot image classification

2025-02-01

1

PRE

AI

DOI：10.1016/j.engappai.2024.109917

Original

Original request for help

Save

Abstract

En 中文

Few-shot image classification aims to learn unseen classes with only a few training samples for each class. However, most existing models still suffer from weak feature representation due to data scarcity. To this end, a novel contrastive learning framework is proposed for few-shot image classification that utilizes patch-wise and class-wise features. Concretely, a semantic patchmix scheme is designed to effectively capture patch-wise features with more discriminative representation. Specifically, a new information noise contrastive estimation loss with modulating factor is proposed to adjust the weights of samples, which is adaptive and trades off different samples. For class-wise features, contrastive prototype learning on two correlated views is leveraged to enhance the generalization of representations. Experiments demonstrate that our method achieves competitive performances on five popular datasets for few-shot image classification. In particular, our method brings a 1.74% improvement in accuracy over state-of-the-art methods on 5-way 1-shot.

Keywords:

Few-shot learning

Contrastive learning

Semantic patchmix

Image classification

Contrastive prototype learning with semantic patchmix for few-shot image classification

Abstract

Journal

Organization