BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learning

arXiv:2403.12986v1 Announce Type: cross
Abstract: Semi-supervised Learning (SSL) reduces the need for extensive annotations in deep learning, but the more realistic challenge of imbalanced data distribution in SSL remains largely unexplored. In Class Imbalanced Semi-supervised Learning (CISSL), the bias introduced by unreliable pseudo-labels can be exacerbated by imbalanced data distributions. Most existing methods address this issue at instance-level through reweighting or resampling, but the performance is heavily limited by their reliance on biased backbone representation. Some other methods do perform …

abstract annotations arxiv bias boosting challenge class cs.cv cs.lg data deep learning distribution feature labels semi-supervised semi-supervised learning ssl supervised learning type via