Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning

arXiv:2309.11930v2 Announce Type: replace-cross
Abstract: In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data. The central challenge is the substantial learning gap between seen and novel categories, as the model learns the former faster due to accurate supervisory information. Moreover, capturing the semantics of unlabeled novel category samples is also challenging due to the missing label information. To address the above issues, we …

arxiv cs.cv cs.lg gap open-world semi-supervised semi-supervised learning supervised learning synchronization type world