Chen Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chen Wei has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Chao Wen
Shanxi University, Taiyuan, China
1 shared publication - Xiaodan Song
Guangzhou Institute of Technology, Xidian University, Guangzhou 510555, China
1 shared publication - Xuemei Xie
School of Artificial Intelligence, Xidian University, Xian, China
1 shared publication - Yuhua Qian
Institute of Big Data Science and Industry, Key Laboratory of Evolutionary Science Intelligence of Shanxi Province, School of Artiicial Intelligence, Shanxi University, Taiyuan, Shanxi Province, China
1 shared publication
Latest Publications
- Open Access
- 22 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (5) , 1-17
Prompt-Based Invertible Mapping Alignment for Unsupervised Domain Adaptation
Large pre-trained vision-language models (VLMs) like CLIP have shown great potential for solving the unsupervised domain adaptation (UDA) problem. Existing prompt learning for UDA based on the unsupervised-trained VLMs requires distribution alignment between source and target domains in the common space for both vision and language branches. However, it is difficult for rough cross-domain alignment to maintain the discriminative semantic structure of both domains. Besides, the coarse features with non-informative noises due to ignoring the pseudo-label noises may cause failures to concentrate on precise semantics alignment. In this work, we propose a Prompt-Based Invertible Mapping Alignment (PIMA) method to incorporate discriminative domain knowledge into prompt learning, which is featured with refined cross-domain alignment in two separate space with a well-kept structure. Specifically, we design an invertible neural network-based homeomorphism mapping, and then achieve distribution alignment through such invertible mapping for connecting source and target visual feature space, which can preserve the data semantic structure. For better semantic alignment in vision-language space, we develop cross-modal implicit contrastive learning module to regularize non-informative features, which aims to find the low-rankness of implicit representation space. We conducted extensive experiments on three benchmark datasets to prove the advantages of our proposed PIMA over state-of-the-art methods.
- 22 May 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 21 (5) , 1-17
Open AccessPrompt-Based Invertible Mapping Alignment for Unsupervised Domain Adaptation
Large pre-trained vision-language models (VLMs) like CLIP have shown great potential for solving the unsupervised domain adaptation (UDA) problem. Existing prompt learning for UDA based on the unsupervised-trained VLMs requires distribution alignment between source and target domains in the common space for both vision and language branches. However, it is difficult for rough cross-domain alignment to maintain the discriminative semantic structure of both domains. Besides, the coarse features with non-informative noises due to ignoring the pseudo-label noises may cause failures to concentrate on precise semantics alignment. In this work, we propose a Prompt-Based Invertible Mapping Alignment (PIMA) method to incorporate discriminative domain knowledge into prompt learning, which is featured with refined cross-domain alignment in two separate space with a well-kept structure. Specifically, we design an invertible neural network-based homeomorphism mapping, and then achieve distribution alignment through such invertible mapping for connecting source and target visual feature space, which can preserve the data semantic structure. For better semantic alignment in vision-language space, we develop cross-modal implicit contrastive learning module to regularize non-informative features, which aims to find the low-rankness of implicit representation space. We conducted extensive experiments on three benchmark datasets to prove the advantages of our proposed PIMA over state-of-the-art methods.