Almanac
technique

Concept-Constrained Prompt Learning

techniqueactiveprovisionalconcept-constrained-prompt-learning-f84187ff·1 events·first seen 4h ago

Aliases: Concept-Constrained Prompt Learning

Co-occurring entities

More like this (12)

Recent events (1)

3arXiv · cs.CL·4h ago·source ↗

Concept-Constrained Prompt Learning (CCPL) improves CLIP few-shot generalization via concept regularization

Researchers propose Concept-Constrained Prompt Learning (CCPL), a lightweight regularization framework for few-shot CLIP adaptation that anchors learnable class prompts to frozen concept-level text prototypes. The method uses cosine consistency objectives in text space and concept dropout to reduce overfitting to base classes, improving base-to-new generalization. Experiments show gains on DTD (+0.6 HM) and EuroSAT (+2.9 HM) over CoOp, with near-neutral results on OxfordPets, suggesting effectiveness is tied to how well concept prototypes align with dataset semantics.