通过关系匹配发现新类别，让已知与未知数据相互启发。
Relational Retrieval: Leveraging Known-Novel Interactions for Generalized Category Discovery
- 用双向知识传递连接有标签和无标签数据
- 在通用和细粒度数据集上达到顶尖性能
- 适合做开放世界识别与新类别发现的研究者
本文从关系检索视角解决广义类别发现（GCD）问题，通过双向知识传递显式关联有标签与无标签数据。现有方法将两类数据分离，错失交互机会；我们提出关系模式一致性（RPC），利用One-vs-All分类器进行软类别/异常分解，设计两个机制：(i) 已知类别保留中，迁移语义行为对齐；(ii) 新类别发现中，利用同类别样本与已知原型间关系不变性，将不可靠伪标签转化为明确的关系模式匹配。该双向设计使有标签数据指导无标签学习，同时通过集体关系签名发现新类别。大量实验表明，RPC在通用和细粒度基准上均达到当前最优表现。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。