CoGe-GCD：重新定义广义类别发现
CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization
清华团队提出CoGe-GCD，解决GCD方法难以泛化到新组合的问题，代码已开源。
CoGe-GCD通过组合泛化重新思考广义类别发现问题。该模型将补丁令牌映射到原始词汇表，通过竞争性令牌-原始分配和信息传递来改进令牌嵌入。
在标准基准测试中，CoGe-GCD在所有类别准确率、未知类别数量估计和几何质量方面均取得一致提升，且计算开销仅略有增加。
CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization
Generalized Category Discovery (GCD) assigns unlabeled instances, mixed with labeled data, to known or novel categories, requiring human-like compositional reasoning: reusing primitives learned from known classes and deciding when new combinations imply new categories. Existing GCD methods operate on unstructured token features and struggle to extrapolate to novel compositions. We propose CoGe-GCD, which rethinks GCD through compositional generalization with two coupled stages. (i) Compositional Perception structures patch tokens by mapping them to a small vocabulary of primitives and refining token embeddings via competitive token-primitive assignment and information passing, yielding coherent groups for discovery. (ii) Generalizing Induction exploits the induced geometric structure and applies a structure-preserving calibration over spatial relations, maintaining probabilistic semantics while improving extrapolation to unseen primitive combinations. CoGe-GCD is implemented as an inductive-bias module between backbone and projection head, without modifying heads or losses, and can be plugged into diverse GCD frameworks. On standard benchmarks, it consistently improves all-class accuracy, unknown-class number estimation, and geometric quality, with marginal computational overhead. Code is available at https://github.com/lytang63/CoGe-GCD.
本条情报归属 AITOP「论文」核心栏目，重点聚焦中国 AI 产业与国产大模型生态。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：CoGe-GCD、GCD、组合泛化、类别发现，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.LG」（@Luyao Tang, Jiewei Zheng, Kunze Huang, Chaoqi Chen, Yue Huang, Cheng Chen），经 AITOP 多维评分管线结构化提炼。
