Multi-level consistency regularization for domain adaptive object detection

doi:10.1007/s00521-023-08677-9

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

	Multi-level consistency regularization for domain adaptive object detection
	Tian, Kun 1,2; Zhang, Chenghao 1,2; Wang, Ying 1; Xiang, Shiming 1,2
刊名	NEURAL COMPUTING & APPLICATIONS
	2023-05-31
页码	16
关键词	Consistency regularization Object detection Domain adaptation
ISSN号	0941-0643
DOI	10.1007/s00521-023-08677-9
通讯作者	Wang, Ying(ying.wang@ia.ac.cn)
英文摘要	To improve the adaptability of detectors, most existing domain adaptation algorithms adopt adversarial learning to align feature distributions between source and target datasets. Different from previous methods, this work explores the possibility of transferring detectors with only source domain data and style information of the target domain. Specifically, we propose three consistency regularizations to enhance the adaptation performance of the detector. First, the source domain and the synthetic domain share the same image content, and the supervision regularization fully exploits the source annotations, which narrows the domain gap and saves labeling costs. Second, prediction regularization improves the robustness of the detector to category semantics and location awareness in different domains. Third, self-discovering feature regularization projects the detector's attention to object-related regions, which are more discriminative than background noise. In addition, our method can cooperate with the classic domain adaptation algorithm to further improve the generalization of the detector, which shows that both the content and style information of target domain images are crucial for the transfer process. Extensive experiments have been conducted on multiple detection benchmarks, including Foggy Cityscapes, Sim10k, KITTI, Clipart, and Watercolor datasets. The favorable performance compared with existing state-of-the-art methods confirms the effectiveness of the proposed consistency regularizations.
资助项目	National Key Research and Development Program of China[2018AAA0100400] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[62076242] ; National Natural Science Foundation of China[62071466] ; National Natural Science Foundation of China[61976208]
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER LONDON LTD
WOS记录号	WOS:000999183100003
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53387]
专题	多模态人工智能系统全国重点实验室
通讯作者	Wang, Ying
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Tian, Kun,Zhang, Chenghao,Wang, Ying,et al. Multi-level consistency regularization for domain adaptive object detection[J]. NEURAL COMPUTING & APPLICATIONS,2023:16.
APA	Tian, Kun,Zhang, Chenghao,Wang, Ying,&Xiang, Shiming.(2023).Multi-level consistency regularization for domain adaptive object detection.NEURAL COMPUTING & APPLICATIONS,16.
MLA	Tian, Kun,et al."Multi-level consistency regularization for domain adaptive object detection".NEURAL COMPUTING & APPLICATIONS (2023):16.