Skip to main content

Neighborhood Contrastive Learning for Novel Class Discovery

A holistic learning framework for Novel Class Discovery (NCD), which adopts contrastive learning to learn discriminate features with both the labeled and unlabeled data. The Neighborhood Contrastive Learning (NCL) framework effectively leverages the local neighborhood in the embedding space, enabling us to take the knowledge from more positive samples and thus improve the clustering accuracy. In addition, we also introduce the Hard Negative Generation (HNG), which leverages the labeled samples to produce informative hard negative samples and brings further advantage to NCL.