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 introduces two mechanisms: (i) for known-class preservation, we transfer semantic behavioral alignment; (ii) for category discovery, we leverage the insight that samples from the same category maintain invariant relationships with known-class prototypes, transforming unreliable pseudo-labeling into well-defined relational pattern matching. This bidirectional design allows labeled data to guide unlabeled learning while discovering novel categories through their collective relational signatures. Extensive experiments demonstrate RPC achieves state-of-the-art performance on both generic and fine-grained benchmarks.

翻译：在本研究中，我们从关系检索的视角解决广义类别发现（GCD）问题，通过双向知识迁移显式耦合标记与未标记数据。现有方法将这两类数据源分开处理，错失了宝贵的交互机会。为此，我们提出关系模式一致性（RPC）方法，实现两者间的相互增强。RPC采用一对多分类器进行软性内部分类/外部分类（ID/OOD）分解，随后引入两种机制：(i) 对于已知类别保持，我们迁移语义行为对齐；(ii) 对于类别发现，我们利用同一类别样本与已知类别原型保持不变关系的洞察，将不可靠的伪标签转化为定义明确的关系模式匹配。这种双向设计使得标记数据能够引导未标记学习，同时通过集体关系特征发现新颖类别。大量实验表明，RPC在通用及细粒度基准测试中均达到了最先进的性能。