Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data

TL;DR

This paper proposes a semi-supervised contrastive learning method that integrates distribution matching between labeled and unlabeled data to improve image classification accuracy.

Contribution

It introduces a novel approach combining distribution matching with contrastive learning for semi-supervised image classification.

Findings

Improved classification accuracy across multiple datasets.

Effective alignment of feature distributions between labeled and unlabeled data.

Enhanced pseudo-label reliability through distribution matching.

Abstract

The advancement of deep learning has greatly improved supervised image classification. However, labeling data is costly, prompting research into unsupervised learning methods such as contrastive learning. In real-world scenarios, fully unlabeled datasets are rare, making semi-supervised learning (SSL) highly relevant in scenarios where a small amount of labeled data coexists with a large volume of unlabeled data. A well-known semi-supervised contrastive learning approach involves assigning pseudo-labels to unlabeled data. This study aims to enhance pseudo-label-based SSL by incorporating distribution matching between labeled and unlabeled feature embeddings to improve image classification accuracy across multiple datasets.