Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

TL;DR

This paper proposes a continuous contrastive learning framework for long-tailed semi-supervised recognition, improving model performance by better handling unlabeled data with diverse distributions.

Contribution

It introduces a probabilistic framework and a novel CCL method that extend contrastive learning to unlabeled data with pseudo-labels, addressing distribution mismatch.

Findings

CCL outperforms previous methods on multiple datasets

Achieves over 4% accuracy improvement on ImageNet-127

Effectively handles diverse unlabeled data distributions

Abstract

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. Our source code is available at https://github.com/zhouzihao11/CCL