CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discovery

arXiv:2304.06928v2 Announce Type: replace
Abstract: We tackle the issue of generalized category discovery (GCD). GCD considers the open-world problem of automatically clustering a partially labelled dataset, in which the unlabelled data may contain instances from both novel categories and labelled classes. In this paper, we address the GCD problem with an unknown category number for the unlabelled data. We propose a framework, named CiPR, to bootstrap the representation by exploiting Cross-instance Positive Relations in the partially labelled data for contrastive …

arxiv cs.ai cs.cv discovery framework generalized instance positive relations type