Attention Guided Multiple Source and Target Domain Adaptation

doi:10.1109/TIP.2020.3031161

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	Attention Guided Multiple Source and Target Domain Adaptation
	Wang, Yuxi 1,2; Zhang, Zhaoxiang 1,2; Hao, Wangli 1,2; Song, Chunfeng 1,2
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2021
卷号	30 页码:892-906
关键词	Semantics Task analysis Generators Generative adversarial networks Feature extraction Visualization Meteorology Domain adaptation multiple source and target domains attention
ISSN号	1057-7149
DOI	10.1109/TIP.2020.3031161
通讯作者	Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
英文摘要	Domain adaptation aims to alleviate the distribution discrepancy between source and target domains. Most conventional methods focus on one target domain setting adapted from one or multiple source domains while neglecting the multi-target domain setting. We argue that different target domains also have complementary information, which is very important for performance improvement. In this paper, we propose an Attention-guided Multiple source-and-target Domain Adaptation (AMDA) method to capture the context dependency information on transferable regions among multiple source and target domains. The innovation points of this paper are as follows: (1) We use numerous adversarial strategies to harvest sufficient information from multiple source and target domains, which extends the generalization and robustness of the feature pools. (2) We propose an intra-domain and inter-domain attention module to explore transferable context information. The proposed attention module can learn domain-invariant representations and reduce the negative transfer by focusing on transferable knowledge. Extensive experiments validate the effectiveness of our method with achieving state-of-the-art performance on several unsupervised domain adaptation datasets.
资助项目	Major Project for New Generation of AI[2018AAA0100400] ; National Natural Science Foundation of China[61836014] ; National Natural Science Foundation of China[61761146004] ; National Natural Science Foundation of China[61773375]
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:000597146900001
资助机构	Major Project for New Generation of AI ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/42673]
专题	自动化研究所_智能感知与计算研究中心
通讯作者	Zhang, Zhaoxiang
作者单位	1.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Wang, Yuxi,Zhang, Zhaoxiang,Hao, Wangli,et al. Attention Guided Multiple Source and Target Domain Adaptation[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:892-906.
APA	Wang, Yuxi,Zhang, Zhaoxiang,Hao, Wangli,&Song, Chunfeng.(2021).Attention Guided Multiple Source and Target Domain Adaptation.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,892-906.
MLA	Wang, Yuxi,et al."Attention Guided Multiple Source and Target Domain Adaptation".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):892-906.