Dual Instance-Consistent Network for Cross-Domain Object Detection

doi:10.1109/TPAMI.2022.3218569

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Dual Instance-Consistent Network for Cross-Domain Object Detection
	Jiao, Yifan 4; Yao, Hantao 5; Xu, Changsheng 1,2,3
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2023-06-01
卷号	45 期号:6 页码:7338-7352
关键词	Feature extraction Object detection Detectors Visualization Proposals Head Task analysis Cross-domain object detection domain-specific description dual instance-consistent network
ISSN号	0162-8828
DOI	10.1109/TPAMI.2022.3218569
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
英文摘要	Cross-domain object detection aims to transfer knowledge from a labeled dataset to an unlabeled dataset. Most existing methods apply a unified embedding model to generate the tightly coupled source and target descriptions for domain alignment, leading to the destroyed feature distribution of the target domain because the embedding model is mainly controlled by the source domain. To reduce the representation bias of the target domain, we apply two independent networks to extract two types of discriminative descriptions with mutual consistency, i.e., a novel Dual Instance-Consistent Network (DICN) is proposed for cross-domain object detection. Especially, Dual Instance-Consistent Module containing the instance mutual consistency between Primary Network and Auxiliary Network is applied to align two domains, where Primary and Auxiliary Networks are used to obtain the source-specific and target-specific information, respectively. The instance mutual consistency consists of two terms: feature consistency and detection consistency, which is applied to align the instance feature and the output of detection head, respectively. With the instance mutual consistency, optimizing the Primary (Auxiliary) Network only with source (target) images by fixing the Auxiliary (Primary) Network can generate the source(target)-specific description. Extensive experiments on several benchmarks demonstrate the effectiveness of the proposed DICN, e.g., obtaining mAP of 44.10% for Cityscapes-> Foggy Cityscapes, AP on car of 76.50% for Cityscapes-> KITTI, MR (2) of 8.87%, 12.66%, 22.27%, and 42.06% for COCOPersons-> Caltech, CityPersons-> Caltech, COCOPersons-> CityPersons, and Caltech-> CityPersons, respectively.
资助项目	National Key Research and Development Program of China[2020AAA0106200] ; National Natural Science Foundation of China[61902399] ; National Natural Science Foundation of China[U21B2044] ; National Natural Science Foundation of China[U1836220] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[62002355] ; National Natural Science Foundation of China[61936005] ; Beijing Natural Science Foundation[L201001] ; Beijing Natural Science Foundation[4222039]
WOS关键词	ALIGNMENT
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:000982475600049
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53519]
专题	多模态人工智能系统全国重点实验室
通讯作者	Xu, Changsheng
作者单位	1.Chinese Acad Sci, Inst Automation, Natl Lab Pattern Recognit, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Peng Cheng Lab, Shenzhen 518055, Peoples R China 4.Nanjing Univ Posts & Telecommun, Sch Commun & Informat Engn, Nanjing, Peoples R China 5.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Jiao, Yifan,Yao, Hantao,Xu, Changsheng. Dual Instance-Consistent Network for Cross-Domain Object Detection[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(6):7338-7352.
APA	Jiao, Yifan,Yao, Hantao,&Xu, Changsheng.(2023).Dual Instance-Consistent Network for Cross-Domain Object Detection.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(6),7338-7352.
MLA	Jiao, Yifan,et al."Dual Instance-Consistent Network for Cross-Domain Object Detection".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.6(2023):7338-7352.