ParaUDA: Invariant Feature Learning With Auxiliary Synthetic Samples for Unsupervised Domain Adaptation

doi:10.1109/TITS.2022.3176397

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	ParaUDA: Invariant Feature Learning With Auxiliary Synthetic Samples for Unsupervised Domain Adaptation
	Zhang, Wenwen 1; Wang, Jiangong2,3 ; Wang, Yutong2,3 ; Wang, Fei-Yue2,3,4,5
发表期刊	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
ISSN	1524-9050
	2022-11-01
卷号	23 期号:11 页码:20217-20229
通讯作者	Wang, Fei-Yue(feiyue.wang@ia.ac.cn)
摘要	Recognizing and locating objects by algorithms are essential and challenging issues for Intelligent Transportation Systems. However, the increasing demand for much labeled data hinders the further application of deep learning-based object detection. One of the optimal solutions is to train the target model with an existing dataset and then adapt it to new scenes, namely Unsupervised Domain Adaptation (UDA). However, most of existing methods at the pixel level mainly focus on adapting the model from source domain to target domain and ignore the essence of UDA to learn domain-invariant feature learning. Meanwhile, almost all methods at the feature level ignore to make conditional distributions matched for UDA while conducting feature alignment between source and target domain. Considering these problems, this paper proposes the ParaUDA, a novel framework of learning invariant representations for UDA in two aspects: pixel level and feature level. At the pixel level, we adopt CycleGAN to conduct domain transfer and convert the problem of original unsupervised domain adaptation to supervised domain adaptation. At the feature level, we adopt an adversarial adaption model to learn domain-invariant representation by aligning the distributions of domains between different image pairs with same mixture distributions. We evaluate our proposed framework in different scenes, from synthetic scenes to real scenes, from normal weather to challenging weather, and from scenes across cameras. The results of all the above experiments show that ParaUDA is effective and robust for adapting object detection models from source scenes to target scenes.
关键词	Adaptation models Representation learning Feature extraction Task analysis Semantics Generative adversarial networks Object detection Object detection unsupervised domain adaptation distribution alignment domain-invariant representation
DOI	10.1109/TITS.2022.3176397
关键词[WOS]	OBJECT DETECTION ; ALIGNMENT ; VISION
收录类别	SCI
语种	英语
资助项目	Key-Area Research and Development Program of Guangdong Province[2020B090921003] ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; National Natural Science Foundation of China[U1811463] ; Key Research and Development Program 2020 of Guangzhou[202007050002]
项目资助者	Key-Area Research and Development Program of Guangdong Province ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; National Natural Science Foundation of China ; Key Research and Development Program 2020 of Guangzhou
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:000880752900025
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：6[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/173211/51297
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Wang, Fei-Yue
作者单位	1.Shaanxi Normal Univ, Sch Comp Sci, Xian 710119, Peoples R China 2.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Macau Univ Sci & Technol, Inst Syst Engn, Macau 999078, Peoples R China 5.Qingdao Acad Intelligent Ind, Qingdao 266000, Peoples R China
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zhang, Wenwen,Wang, Jiangong,Wang, Yutong,et al. ParaUDA: Invariant Feature Learning With Auxiliary Synthetic Samples for Unsupervised Domain Adaptation[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2022,23(11):20217-20229.
APA	Zhang, Wenwen,Wang, Jiangong,Wang, Yutong,&Wang, Fei-Yue.(2022).ParaUDA: Invariant Feature Learning With Auxiliary Synthetic Samples for Unsupervised Domain Adaptation.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,23(11),20217-20229.
MLA	Zhang, Wenwen,et al."ParaUDA: Invariant Feature Learning With Auxiliary Synthetic Samples for Unsupervised Domain Adaptation".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 23.11(2022):20217-20229.