Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning

arXiv:2312.15702v2 Announce Type: replace
Abstract: We address the challenging problem of Long-Tailed Semi-Supervised Learning (LTSSL) where labeled data exhibit imbalanced class distribution and unlabeled data follow an unknown distribution. Unlike in balanced SSL, the generated pseudo-labels are skewed towards head classes, intensifying the training bias. Such a phenomenon is even amplified as more unlabeled data will be mislabeled as head classes when the class distribution of labeled and unlabeled datasets are mismatched. To solve this problem, we propose a novel …

arxiv cs.cv experts semi-supervised semi-supervised learning supervised learning type