现代电子技术2024，Vol.47Issue(18)：41-46,6.DOI:10.16652/j.issn.1004-373x.2024.18.007
基于域特定特征的CLIP提示优化算法
CLIP prompt optimization algorithm based on domain-specific feature
张跃文 1王九杭 1覃荣华2
作者信息
- 1. 中国科学院上海微系统与信息技术研究所,上海 201800||中国科学院大学,北京 100049
- 2. 中国科学院上海微系统与信息技术研究所,上海 201800
- 折叠
摘要
Abstract
When the testing data and training data follow different distributions,the neural network can undergo domain shift.The goal of domain generalization(DG)is to solve this problem by learning a general model that can handle unknown domains.Previous methods can extract domain-invariant features by means of data enhancement or feature space alignment,but new domain-specific features can be generated in the process of extraction,resulting in poor model generalization performance.On this basis,a simple and effective framework ERCLIP(extracting and removing domain-specific features for CLIP)is proposed to realize the application of large-scale pre-training model CLIP in DG.ERCLIP can realize precise semantic description of images by actively extracting domain specific features and incorporating them into text prompts.The experimental results on the public datasets OfficeHome,VLCS,and PACS show that ERCLIP can realize the best results among all algorithms,with an average accuracy of 83.4%on OfficeHome,83.5%on VLCS,and 96.5%on PACS.关键词
域不变特征/ERCLIP/领域泛化/神经网络/特征提取/文本提示Key words
domain-invariant feature/ERCLIP/domain generalization/neural network/feature extraction/text prompt分类
电子信息工程引用本文复制引用
张跃文,王九杭,覃荣华..基于域特定特征的CLIP提示优化算法[J].现代电子技术,2024,47(18):41-46,6.
