Few-Shot Classification with Contrastive Learning

TL;DR

This paper introduces a novel contrastive learning framework for few-shot classification that integrates contrastive learning into both pre-training and meta-training stages, enhancing representation transferability and achieving competitive results.

Contribution

It proposes a unified contrastive learning approach with a self-supervised loss and cross-view episodic training, fully exploiting contrastive learning in both FSL stages.

Findings

Achieves competitive results on three benchmark datasets.

Enhances transferability of representations through novel contrastive strategies.

Demonstrates the effectiveness of integrated contrastive learning in FSL.

Abstract

A two-stage training paradigm consisting of sequential pre-training and meta-training stages has been widely used in current few-shot learning (FSL) research. Many of these methods use self-supervised learning and contrastive learning to achieve new state-of-the-art results. However, the potential of contrastive learning in both stages of FSL training paradigm is still not fully exploited. In this paper, we propose a novel contrastive learning-based framework that seamlessly integrates contrastive learning into both stages to improve the performance of few-shot classification. In the pre-training stage, we propose a self-supervised contrastive loss in the forms of feature vector vs. feature map and feature map vs. feature map, which uses global and local information to learn good initial representations. In the meta-training stage, we propose a cross-view episodic training mechanism to perform the nearest centroid classification on two different views of the same episode and adopt a distance-scaled contrastive loss based on them. These two strategies force the model to overcome the bias between views and promote the transferability of representations. Extensive experiments on three benchmark datasets demonstrate that our method achieves competitive results.