CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization

2026-09-09

AI Summary

本文提出CoGe-GCD方法，通过结构化感知和归纳推广两个阶段，解决现有GCD方法难以处理新颖组合的问题，提高分类准确性和未知类别估计。

Abstract

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.

Problem

• Generalized Category Discovery
• compositional generalization
• novel compositions
• extrapolation
• unlabeled instances

Innovation

• Compositional Generalization
• Token-Primitive Assignment
• Structure-Preserving Calibration