提出连续对比学习方法，解决长尾半监督识别中标签分布不均问题。
Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
- 基于高斯核密度估计构建类别平衡对比损失，统一多种长尾学习方法。
- 通过平滑伪标签逐步对齐模型预测与真实标签分布，提升性能。
- 在多个数据集上超越现有方法，图像网-127提升超4%。
长尾半监督学习在标注数据有限且标签分布极不均衡的情况下面临严峻挑战。当前最先进的长尾半监督学习方法高度依赖高质量伪标签来处理大规模无标签数据，但这些方法往往忽视神经网络学习到的表征特性，且难以应对现实场景中无标签数据分布与标注数据不同的情况。本文提出一种新颖的概率框架，统一了近期多种长尾学习方案。该框架通过高斯核密度估计推导出类别平衡的对比损失，并引入连续对比学习（CCL）方法，利用可靠且平滑的伪标签将框架扩展至无标签数据。通过逐步估计底层标签分布并优化其与模型预测的一致性，有效缓解了真实场景下无标签数据分布多样性的问题。大量实验表明，在多个具有不同无标签数据分布的数据集上，CCL持续优于现有最先进方法，在ImageNet-127数据集上实现超过4%的性能提升。源代码已开源。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。