Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

• Published in: arXiv.org
• Main Authors: Zi-Hao Zhou, Fang, Siyuan, Zi-Jing Zhou, Tong, Wei, Wan, Yuanyu, Min-Ling, Zhang
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 08.10.2024
• Subjects: Datasets; Estimation; Labels; Neural networks; Semi-supervised learning; Source code

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 oft...