Dual Structural Knowledge Interaction for Domain Adaptation

doi:10.1109/TMM.2023.3245420

	Dual Structural Knowledge Interaction for Domain Adaptation
	Zuo, Yukun 1; Yao, Hantao2 ; Zhuang, Liansheng 1; Xu, Changsheng2,3
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
	2023
卷号	25 页码:9057-9070
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
摘要	Domain adaptation aims to transfer knowledge from a label-rich source domain to an unlabeled target domain. A common strategy is to assign pseudo-labels to unlabeled target samples for performing representation learning. However, most existing methods only apply the source-guided classifier to generate the source-biased pseudo-labels for self-training, leading to biased target representations. Moreover, the generated pseudo-labels ignore the manifold assumption that neighboring samples are likely to have the same labels. To address the above problem, we formulate a novel structural knowledge to assign target-oriented and manifold-guided pseudo-labels for unlabeled target samples. The structural knowledge consists of cluster-based knowledge and locality-based knowledge. The cluster-based knowledge denotes the label consistency between the target samples and the non-parametric target cluster centers, making the pseudo-labels target-oriented. The locality-based knowledge constrains the target sample and its neighbors to satisfy the manifold assumption. As the neighbors contain the source and target samples, the source and target locality-based knowledge are utilized to boost the descriptions. With the structural knowledge, we propose a novel Dual Structural Knowledge Interaction (DSKI) framework for domain adaptation. For generating aligned and discriminative features, knowledge consistency constraint and instance mutual constraint are proposed in DSKI. Evaluations on three benchmarks demonstrate the effectiveness of the Dual Structural Knowledge Interaction, e.g., 74.9%, 87.7%, and 90.8% for Office-Home, VisDa-2017, and Office-31, respectively.
关键词	Manifolds Feature extraction Adaptation models Representation learning Task analysis Semisupervised learning Pattern recognition Domain adaptation structural knowledge dual structural knowledge interaction
DOI	10.1109/TMM.2023.3245420
关键词[WOS]	ALIGNMENT
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China
项目资助者	National Key Research and Development Program of China
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:001133324200032
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/54830
专题	多模态人工智能系统全国重点实验室
通讯作者	Xu, Changsheng
作者单位	1.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zuo, Yukun,Yao, Hantao,Zhuang, Liansheng,et al. Dual Structural Knowledge Interaction for Domain Adaptation[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:9057-9070.
APA	Zuo, Yukun,Yao, Hantao,Zhuang, Liansheng,&Xu, Changsheng.(2023).Dual Structural Knowledge Interaction for Domain Adaptation.IEEE TRANSACTIONS ON MULTIMEDIA,25,9057-9070.
MLA	Zuo, Yukun,et al."Dual Structural Knowledge Interaction for Domain Adaptation".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):9057-9070.