Progressive Decision Boundary Shifting for Unsupervised Domain Adaptation

doi:10.1109/TNNLS.2024.3431283

	Progressive Decision Boundary Shifting for Unsupervised Domain Adaptation
	Li, Liang 1; Lu, Tongyu 2; Sun, Yaoqi 3; Gao, Yuhan 4; Yan, Chenggang 2; Hu, Zhenghui 4; Huang, Qingming 5,6
	2024-08-09
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
页码	12
摘要	Unsupervised domain adaptation (UDA) is attracting more attention from researchers for boosting the task-specific generalization on target domain. It focuses on addressing the domain shift between the labeled source domain and the unlabeled target domain. Recent biclassifier-based UDA models perform category-level alignment to reduce domain shift, and meanwhile, self-training is used for improving the discriminability of target instances. However, the error accumulation problem of instances with high semantic uncertainty may cause discriminability degradation and category-level misalignment. To solve this issue, we design the progressive decision boundary shifting algorithm, where stable category information of target instances is explored for learning a discriminability structure on target domain. Specifically, we first model the semantic uncertainty of instances by progressively shifting decision boundaries of category. Then, we introduce the uncertainty decoupling in a contrastive manner, where the discriminative information is learned from the source domain for instance with low semantic uncertainty. Furthermore, we minimize the predictive entropy of instances with high semantic uncertainty to reduce their prediction confidence. Extensive experiments on three popular datasets show that our model outperforms the current state-of-the-art (SOTA) UDA methods.
关键词	Uncertainty Feature extraction Semantics Task analysis Training Adversarial machine learning Symbols Domain shifting progressive decision boundary self-learning unsupervised domain adaptation (UDA)
DOI	10.1109/TNNLS.2024.3431283
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62322211] ; National Natural Science Foundation of China[62336008] ; National Natural Science Foundation of China[62236008] ; National Natural Science Foundation of China[U21B2038] ; National Natural Science Foundation of China[U21B2024] ; Youth Innovation Promotion Association of Chinese Academy of Sciences[2020108] ; The Pioneer and Leading Goose Research and Development Program of Zhejiang Province[2024C01023]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:001288144900001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39672
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yan, Chenggang; Hu, Zhenghui
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100045, Peoples R China 2.Hangzhou Dianzi Univ, Sch Automat, Hangzhou 310018, Peoples R China 3.Hangzhou Dianzi Univ, Lishui Inst, Hangzhou, Zhejiang, Peoples R China 4.Beihang Univ, Hangzhou Innovat Inst, Beijing, Zhejiang, Peoples R China 5.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 6.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Liang,Lu, Tongyu,Sun, Yaoqi,et al. Progressive Decision Boundary Shifting for Unsupervised Domain Adaptation[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2024:12.
APA	Li, Liang.,Lu, Tongyu.,Sun, Yaoqi.,Gao, Yuhan.,Yan, Chenggang.,...&Huang, Qingming.(2024).Progressive Decision Boundary Shifting for Unsupervised Domain Adaptation.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,12.
MLA	Li, Liang,et al."Progressive Decision Boundary Shifting for Unsupervised Domain Adaptation".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2024):12.