SOURCE-LINKED INTELLIGENCE

CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global