CDAD-Net: Bridging Domain Gaps in Generalized Category Discovery

arXiv:2404.05366v1 Announce Type: new
Abstract: In Generalized Category Discovery (GCD), we cluster unlabeled samples of known and novel classes, leveraging a training dataset of known classes. A salient challenge arises due to domain shifts between these datasets. To address this, we present a novel setting: Across Domain Generalized Category Discovery (AD-GCD) and bring forth CDAD-NET (Class Discoverer Across Domains) as a remedy. CDAD-NET is architected to synchronize potential known class samples across both the labeled (source) and unlabeled (target) datasets, …

abstract arxiv challenge cluster cs.cv dataset datasets discovery domain generalized novel samples training type