Margin-Based Adversarial Joint Alignment Domain Adaptation

doi:10.1109/TCSVT.2021.3081729

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	Margin-Based Adversarial Joint Alignment Domain Adaptation
	Zuo, Yukun 1; Yao, Hantao 3; Zhuang, Liansheng 1; Xu, Changsheng 2,3
刊名	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2022-04-01
卷号	32 期号:4 页码:2057-2067
关键词	Feature extraction Adaptation models Image reconstruction Generative adversarial networks Semisupervised learning Data models Training Domain adaptation joint alignment module margin-based generative module
ISSN号	1051-8215
DOI	10.1109/TCSVT.2021.3081729
通讯作者	Xu, Changsheng(csxu@nlpria.ac.cn)
英文摘要	Domain adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain, which has different data distribution with the source domain. Most of the existing methods focus on aligning the data distribution between the source and target domains but ignore the discrimination of the feature space among categories, leading the samples close to the decision boundary to be misclassified easily. To address the above issue, we propose a Margin-based Adversarial Joint Alignment (MAJA) to constrain the feature spaces of source and target domains to be aligned and discriminative. The proposed MAJA consists of two components: joint alignment module and margin-based generative module. The joint alignment module is proposed to align the source and target feature spaces by considering the joint distribution of features and labels. Therefore, the embedding features and the corresponding labels treated as pair data are applied for domain alignment. Furthermore, the margin-based generative module is proposed to boost the discrimination of the feature space, i.e., make all samples as far away from the decision boundary as possible. The margin-based generative module first employs the Generative Adversarial Networks (GAN) to generate a lot of fake images for each category, then applies the adversarial learning to enlarge and reduce the category margin for the true images and generated fake images, respectively. The evaluations on three benchmarks, e.g., small image datasets, VisDA-2017, and Office-31, verify the effectiveness of the proposed method.
资助项目	National Key Research and Development Program of China[2018AAA0102205] ; National Natural Science Foundation of China[61902399] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[U1836220] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[61832002] ; National Natural Science Foundation of China[61720106006] ; National Natural Science Foundation of China[U20B2070] ; National Natural Science Foundation of China[61976199] ; Beijing Natural Science Foundation[L201001] ; Key Research Program of Frontier Sciences, Chinese Academy of Sciences (CAS)[QYZDJSSW-JSC039]
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000778973700030
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Key Research Program of Frontier Sciences, Chinese Academy of Sciences (CAS)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48255]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
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.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zuo, Yukun,Yao, Hantao,Zhuang, Liansheng,et al. Margin-Based Adversarial Joint Alignment Domain Adaptation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2022,32(4):2057-2067.
APA	Zuo, Yukun,Yao, Hantao,Zhuang, Liansheng,&Xu, Changsheng.(2022).Margin-Based Adversarial Joint Alignment Domain Adaptation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,32(4),2057-2067.
MLA	Zuo, Yukun,et al."Margin-Based Adversarial Joint Alignment Domain Adaptation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 32.4(2022):2057-2067.