Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery

arXiv:2404.08995v1 Announce Type: new
Abstract: Generalized Class Discovery (GCD) aims to dynamically assign labels to unlabelled data partially based on knowledge learned from labelled data, where the unlabelled data may come from known or novel classes. The prevailing approach generally involves clustering across all data and learning conceptions by prototypical contrastive learning. However, existing methods largely hinge on the performance of clustering algorithms and are thus subject to their inherent limitations. Firstly, the estimated cluster number is often smaller than …

arxiv beyond class cs.ai cs.cv cs.lg discovery generalized probe type