Class-Aware Visual Prompt Learning for Vision Language Models.

Saved in:

Bibliographic Details
Title:	Class-Aware Visual Prompt Learning for Vision Language Models.
Authors:	Sihui Zhang¹, Zhijiang Li¹ lizhijiang@whu.edu.cn
Source:	Journal of Imaging Science & Technology. May/Jun2025, Vol. 69 Issue 3, p1-7. 7p.
Subjects:	Language models, Visual learning, Recognition (Psychology), Task performance, Generalization
Abstract:	Vision-language pre-trained (VLP) models, such as CLIP, have exhibited remarkable performance in downstream tasks with excellent generalization capabilities. Meanwhile, textual and visual prompt learning have been widely adopted to enhance VLP model performance in downstream tasks. However, a challenging issue in visual prompt learning is the inferior ability on few-shot recognition tasks, the inability to capture specific class information. Thus, we propose a class-aware visual prompt learning method to enhance the perceptual abilities of VLP model with an independent class prompting module, which consists of trainable prompts for each class. As class-aware prompts tend to be inaccurate in the training process, we developed an intra-class compactness loss and inter-class dispersion loss to enhance the intra-class consistency. Finally, we introduced attention-based adapter layers to tackle the prompt selection issue. Extensive experiments demonstrated that our method achieved superior efficiency and effectiveness, surpassing previous visual prompting methods in a series of downstream datasets. [ABSTRACT FROM AUTHOR]
	Copyright of Journal of Imaging Science & Technology is the property of International Society for Imaging Science & Technology and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Vision-language pre-trained (VLP) models, such as CLIP, have exhibited remarkable performance in downstream tasks with excellent generalization capabilities. Meanwhile, textual and visual prompt learning have been widely adopted to enhance VLP model performance in downstream tasks. However, a challenging issue in visual prompt learning is the inferior ability on few-shot recognition tasks, the inability to capture specific class information. Thus, we propose a class-aware visual prompt learning method to enhance the perceptual abilities of VLP model with an independent class prompting module, which consists of trainable prompts for each class. As class-aware prompts tend to be inaccurate in the training process, we developed an intra-class compactness loss and inter-class dispersion loss to enhance the intra-class consistency. Finally, we introduced attention-based adapter layers to tackle the prompt selection issue. Extensive experiments demonstrated that our method achieved superior efficiency and effectiveness, surpassing previous visual prompting methods in a series of downstream datasets. [ABSTRACT FROM AUTHOR]
ISSN:	10623701
DOI:	10.2352/J.ImagingSci.Technol.2025.69.3.030415