Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning

doi:10.1109/TIP.2020.3031220

CORC > 自动化研究所 > 中国科学院自动化研究所 > 精密感知与控制研究中心 > 人工智能与机器学习

	Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning
	Tian, Lei 1,3; Tang, Yongqiang 1; Hu, Liangchen 2; Ren, Zhida 1,3; Zhang, Wensheng 1,3
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2020
卷号	29 页码:9703-9718
关键词	Domain adaptation class centroid matching local manifold self-learning
ISSN号	1057-7149
DOI	10.1109/TIP.2020.3031220
通讯作者	Zhang, Wensheng(zhangwenshengia@hotmail.com)
英文摘要	Domain adaptation has been a fundamental technology for transferring knowledge from a source domain to a target domain. The key issue of domain adaptation is how to reduce the distribution discrepancy between two domains in a proper way such that they can be treated indifferently for learning. In this paper, we propose a novel domain adaptation approach, which can thoroughly explore the data distribution structure of target domain. Specifically, we regard the samples within the same cluster in target domain as a whole rather than individuals and assigns pseudo-labels to the target cluster by class centroid matching. Besides, to exploit the manifold structure information of target data more thoroughly, we further introduce a local manifold self-learning strategy into our proposal to adaptively capture the inherent local connectivity of target samples. An efficient iterative optimization algorithm is designed to solve the objective function of our proposal with theoretical convergence guarantee. In addition to unsupervised domain adaptation, we further extend our method to the semi-supervised scenario including both homogeneous and heterogeneous settings in a direct but elegant way. Extensive experiments on seven benchmark datasets validate the significant superiority of our proposal in both unsupervised and semi-supervised manners.
资助项目	Key-Area Research and Development Program of Guangdong Province[2019B010153002] ; National Natural Science Foundation of China[U1636220] ; National Natural Science Foundation of China[61961160707] ; National Natural Science Foundation of China[61772525]
WOS关键词	KERNEL
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000583696200003
资助机构	Key-Area Research and Development Program of Guangdong Province ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/41752]
专题	精密感知与控制研究中心_人工智能与机器学习
通讯作者	Zhang, Wensheng
作者单位	1.Chinese Acad Sci, Res Ctr Precis Sensing & Control, Inst Automat, Beijing 100190, Peoples R China 2.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China
推荐引用方式 GB/T 7714	Tian, Lei,Tang, Yongqiang,Hu, Liangchen,et al. Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:9703-9718.
APA	Tian, Lei,Tang, Yongqiang,Hu, Liangchen,Ren, Zhida,&Zhang, Wensheng.(2020).Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,9703-9718.
MLA	Tian, Lei,et al."Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):9703-9718.