AI RESEARCH
PartCo: Part-Level Correspondence Priors Enhance Category Discovery
arXiv CS.CV
•
ArXi:2509.22769v2 Announce Type: replace Generalized Category Discovery (GCD) aims to identify both known and novel categories within unlabeled data by leveraging a set of labeled examples from known categories. Existing GCD methods primarily depend on semantic labels and global image representations, often overlooking the detailed part-level cues that are crucial for distinguishing closely related categories. In this paper, we