Seek Common Ground While Reserving Differences: A Model-Agnostic Module for Noisy Domain Adaptation

doi:10.1109/TMM.2021.3097495

	Seek Common Ground While Reserving Differences: A Model-Agnostic Module for Noisy Domain Adaptation
	Zuo, Yukun 1; Yao, Hantao2 ; Zhuang, Liansheng 1; Xu, Changsheng2,3
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
	2022
卷号	24 页码:1020-1030
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
摘要	Noisy domain adaptation aims to solve the problem that the source dataset contains noisy labels in domain adaptation. Previous methods handle noisy labels by selecting the small-loss samples with inconsistent predictions between two models and discarding the consistent samples, resulting in many noises contained in the selected samples. By jointly considering the consistent and inconsistent samples, we propose a model-agnostic module, named Seek Common Ground While Reserving Differences (SCGWRD), to reduce the impact of noisy samples. The proposed SCGWRD module consists of Seek Common Ground (SCG) component and Reserve Differences (RD) component by utilizing the outputs of two symmetrical domain adaptation models. As the common samples with consistent predictions between two models are more likely to be clean samples, the SCG component applies the small-loss strategy to select the reliable samples with consistent predictions. Unlike SCG, the RD component maintains the divergences between two models with mutual learning and reduces the effect of noisy data using the samples with different predictions and small losses. Evaluations on three benchmarks demonstrate the effectiveness and robustness of the proposed SCGWRD module for noisy domain adaptation.
关键词	Noise measurement Adaptation models Predictive models Reliability Task analysis Standards Data models Noisy domain adaptation Seek common ground component Reserve differences component
DOI	10.1109/TMM.2021.3097495
收录类别	SCI
语种	英语
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] ; National Natural Science Foundation of China[62036012] ; Beijing Natural Science Foundation[L201001] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Key Research Program of Frontier Sciences, CAS
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:000764821800001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	机器学习
引用统计	被引频次：3[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/173211/48012
专题	多模态人工智能系统全国重点实验室_多媒体计算
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, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Zuo, Yukun,Yao, Hantao,Zhuang, Liansheng,et al. Seek Common Ground While Reserving Differences: A Model-Agnostic Module for Noisy Domain Adaptation[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2022,24:1020-1030.
APA	Zuo, Yukun,Yao, Hantao,Zhuang, Liansheng,&Xu, Changsheng.(2022).Seek Common Ground While Reserving Differences: A Model-Agnostic Module for Noisy Domain Adaptation.IEEE TRANSACTIONS ON MULTIMEDIA,24,1020-1030.
MLA	Zuo, Yukun,et al."Seek Common Ground While Reserving Differences: A Model-Agnostic Module for Noisy Domain Adaptation".IEEE TRANSACTIONS ON MULTIMEDIA 24(2022):1020-1030.