Domain-Aware Graph Network for Bridging Multi-Source Domain Adaptation

doi:10.1109/TMM.2024.3361729

	Domain-Aware Graph Network for Bridging Multi-Source Domain Adaptation
	Yuan, Jin 1,2; Hou, Feng 3,4; Yang, Ying 5; Zhang, Yang 5; Shi, Zhongchao 5; Geng, Xin 1,2; Fan, Jianping 5; He, Zhiqiang 3,4; Rui, Yong 1,2,5
	2024
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
卷号	26 页码:7210-7224
摘要	Domain adaptation (DA) addresses the challenge of distribution discrepancy between the training and test data, while multi-source domain adaptation (MSDA) is particularly appealing for realistic scenarios. With the emergence of extensive unlabeled datasets, self-supervised learning has gained significant popularity in deep learning. It is noteworthy that multi-source domain adaptation and self-supervised learning share a common objective: leveraging unlabeled data to acquire more informative representations. However, conventional self-supervised learning encounters two main limitations. Firstly, the traditional pretext task falls to transfer fine-grained knowledge to downstream task with general representation learning. Secondly, the scheme of the same feature extractor with distinct prediction heads makes the cross-task knowledge exchange and information sharing ineffective. In order to tackle these challenges, we introduce a novel approach called Domain-Aware Graph Network (DAGNet). DAGNet utilizes a graph neural network as a bridge to facilitate efficient cross-task knowledge exchange. By employing a mask token strategy, we enhance the robustness of representations by selectively masking certain domain or self-supervised information. In terms of datasets, the uneven and style-based domain shifts in current datasets make it challenging to measure the model's domain adaptation performance in real-world applications. To address this issue, we introduce a benchmark dataset DomainVerse with continuous spatio-temporal domain shifts encountered in the real world. Our extensive experiments demonstrate that DAGNet achieves state-of-the-art performance not only on mainstream multi-source domain adaptation datasets but also on different settings within DomainVerse.
关键词	Task analysis Feature extraction Graph neural networks Adaptation models Self-supervised learning Multitasking Image color analysis Multi-source domain adaptation self-supervised learning graph neural network real-world applications
DOI	10.1109/TMM.2024.3361729
收录类别	SCI
语种	英语
资助项目	AI Lab
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:001209811000018
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/2XEOYT63/38991
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Geng, Xin; Rui, Yong
作者单位	1.Southeast Univ, Sch Comp Sci & Engn, Minist Educ, Nanjing 211189, Peoples R China 2.Southeast Univ, Key Lab Comp Network & Informat Integrat, Minist Educ, Nanjing 211189, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100000, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100000, Peoples R China 5.Lenovo Res, AI Lab, Beijing 100000, Peoples R China
推荐引用方式 GB/T 7714	Yuan, Jin,Hou, Feng,Yang, Ying,et al. Domain-Aware Graph Network for Bridging Multi-Source Domain Adaptation[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2024,26:7210-7224.
APA	Yuan, Jin.,Hou, Feng.,Yang, Ying.,Zhang, Yang.,Shi, Zhongchao.,...&Rui, Yong.(2024).Domain-Aware Graph Network for Bridging Multi-Source Domain Adaptation.IEEE TRANSACTIONS ON MULTIMEDIA,26,7210-7224.
MLA	Yuan, Jin,et al."Domain-Aware Graph Network for Bridging Multi-Source Domain Adaptation".IEEE TRANSACTIONS ON MULTIMEDIA 26(2024):7210-7224.