AI RESEARCH
Relational Retrieval: Leveraging Known-Novel Interactions for Generalized Category Discovery
arXiv CS.AI
•
ArXi:2605.09420v1 Announce Type: cross In this study, we tackle Generalized Category Discovery (GCD) via a Relational Retrieval perspective, explicitly coupling labeled and unlabeled data through bidirectional knowledge transfer. While existing methods treat these sources separately, missing valuable interaction opportunities, we propose Relational Pattern Consistency (RPC) that enables mutual enhancement. RPC employs One-vs-All classifiers for soft ID/OOD decomposition, then