Uncertainty Modeling for Robust Domain Adaptation Under Noisy Environments

doi:10.1109/TMM.2022.3205457

CSpace

	Uncertainty Modeling for Robust Domain Adaptation Under Noisy Environments
	Zhuo, Junbao 1; Wang, Shuhui 1,2; Huang, Qingming 1,2,3
	2023
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
卷号	25 页码:6157-6170
摘要	In this paper, we tackle the task of domain adaptation under noisy environments; this is a practical and challenging problem in which the source domain is corrupted with noise in its labels, its features, or both. Noise in the source domain leads to inaccurate visual representations and makes it harder to estimate and reduce the domain discrepancy between the source and target domains, resulting in severe performance degradation in the target domain. These challenges can be addressed with offline source sample selection following robust domain discrepancy reduction. To achieve reliable sample selection, we model the uncertainty in the predictions of a convolutional neural network (CNN) classifier and reweight the classification loss by this uncertainty. Such a reweighting mechanism reduces the contribution of noise, leading to improved noise robustness. We further propose UncertaintyRank, a novel regularizer, to encourage the uncertainty to be more sensitive to noisy labels, as label corruption brings more severe degradation. The uncertainty is also aggregated with the classification loss to eliminate the adverse effects of noisy representations while estimating the domain discrepancy. Extensive experiments validate the effectiveness of our method and verify that it performs favorably against existing state-of-the-art methods.
关键词	Domain Adaptation Uncertainty Noisy Label Transfer Learning Deep Learning
DOI	10.1109/TMM.2022.3205457
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2018AAA0102000] ; National Natural Science Foundation of China[62022083] ; National Natural Science Foundation of China[U21B2038] ; National Natural Science Foundation of China[61931008] ; Fundamental Research Funds for the Central Universities
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:001098831500037
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
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://119.78.100.204/handle/2XEOYT63/38070
专题	中国科学院计算技术研究所
通讯作者	Wang, Shuhui
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Peng Cheng Lab, Shenzhen 518066, Peoples R China 3.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China
推荐引用方式 GB/T 7714	Zhuo, Junbao,Wang, Shuhui,Huang, Qingming. Uncertainty Modeling for Robust Domain Adaptation Under Noisy Environments[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:6157-6170.
APA	Zhuo, Junbao,Wang, Shuhui,&Huang, Qingming.(2023).Uncertainty Modeling for Robust Domain Adaptation Under Noisy Environments.IEEE TRANSACTIONS ON MULTIMEDIA,25,6157-6170.
MLA	Zhuo, Junbao,et al."Uncertainty Modeling for Robust Domain Adaptation Under Noisy Environments".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):6157-6170.