TARP: Text-Augmented Re-centered Projection for few-shot CLIP adaptation

Journal of Information and Intelligence · Elsevier

Аннотация

Publication date: November–December 2026 Source: Computer Vision and Image Understanding, Volume 273 Author(s): Chunxu Liu, Guowei Tang, Rui Zhao, Limin Wang

Читать у издателя →

Похожие статьи