Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to overfit to seen classes, failing to generalize to unseen classes....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-08
Hauptverfasser:	Kan, Baoshuo, Wang, Teng, Lu, Wenpeng, Xiantong Zhen, Guan, Weili, Zheng, Feng
Format:	Artikel
Sprache:	eng
Schlagworte:	Coders Image classification State of the art Vision Visual discrimination Visual tasks
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!