OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning. (arXiv:2207.02261v1 [cs.CV])

Semi-supervised learning (SSL) is one of the dominant approaches to address
the annotation bottleneck of supervised learning. Recent SSL methods can
effectively leverage a large repository of unlabeled data to improve
performance while relying on a small set of labeled data. One common assumption
in most SSL methods is that the labeled and unlabeled data are from the same
underlying data distribution. However, this is hardly the case in many
real-world scenarios, which limits their applicability. In this work, instead, …

arxiv cv learning semi-supervised semi-supervised learning supervised learning