Unified Optimal Transport Framework for Universal Domain Adaptation

	Unified Optimal Transport Framework for Universal Domain Adaptation
	Chang, Wanxing1 ; Shi, Ye1,3 ; Tuan, Hoang Duong 2; Wang, Jingya1,3
	2022
会议录名称	ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022)
ISSN	1049-5258
摘要	Universal Domain Adaptation (UniDA) aims to transfer knowledge from a source domain to a target domain without any constraints on label sets. Since both domains may hold private classes, identifying target common samples for domain alignment is an essential issue in UniDA. Most existing methods require manually specified or hand-tuned threshold values to detect common samples thus they are hard to extend to more realistic UniDA because of the diverse ratios of common classes. Moreover, they cannot recognize different categories among target-private samples as these private samples are treated as a whole. In this paper, we propose to use Optimal Transport (OT) to handle these issues under a unified framework, namely UniOT. First, an OT-based partial alignment with adaptive filling is designed to detect common classes without any predefined threshold values for realistic UniDA. It can automatically discover the intrinsic difference between common and private classes based on the statistical information of the assignment matrix obtained from OT. Second, we propose an OT-based target representation learning that encourages both global discrimination and local consistency of samples to avoid the over-reliance on the source. Notably, UniOT is the first method with the capability to automatically discover and recognize private categories in the target domain for UniDA. Accordingly, we introduce a new metric H-3-score to evaluate the performance in terms of both accuracy of common samples and clustering performance of private ones. Extensive experiments clearly demonstrate the advantages of UniOT over a wide range of state-of-the-art methods in UniDA.
会议名称	36th Conference on Neural Information Processing Systems (NeurIPS)
出版地	10010 NORTH TORREY PINES RD, LA JOLLA, CALIFORNIA 92037 USA
会议地点	null,null,ELECTR NETWORK
会议日期	NOV 28-DEC 09, 2022
URL	查看原文
收录类别	EI ; CPCI-S
语种	英语
资助项目	Shanghai Sailing Program["21YF1429400","22YF1428800"] ; Shanghai Local College Capacity Building Program[23010503100]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems
WOS记录号	WOS:001213811609031
出版者	NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/317217
专题	信息科学与技术学院_PI研究组_石野组信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_汪婧雅组
作者单位	1.ShanghaiTech University, China; 2.University of Technology Sydney, Australia; 3.Shanghai Engineering Research Center of Intelligent Vision and Imaging, China
第一作者单位	上海科技大学
第一作者的第一单位	上海科技大学
推荐引用方式 GB/T 7714	Chang, Wanxing,Shi, Ye,Tuan, Hoang Duong,et al. Unified Optimal Transport Framework for Universal Domain Adaptation[C]. 10010 NORTH TORREY PINES RD, LA JOLLA, CALIFORNIA 92037 USA:NEURAL INFORMATION PROCESSING SYSTEMS (NIPS),2022.