SAN: Selective Alignment Network for Cross-Domain Pedestrian Detection

doi:10.1109/TIP.2021.3049948

	SAN: Selective Alignment Network for Cross-Domain Pedestrian Detection
	Jiao, Yifan 1; Yao, Hantao2 ; Xu, Changsheng2,3
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2021
卷号	30 页码:2155-2167
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
摘要	Cross-domain pedestrian detection, which has been attracting much attention, assumes that the training and test images are drawn from different data distributions. Existing methods focus on aligning the descriptions of whole candidate instances between source and target domains. Since there exists a giant visual difference among the candidate instances, aligning whole candidate instances between two domains cannot overcome the inter-instance difference. Compared with aligning the whole candidate instances, we consider that aligning each type of instances separately is a more reasonable manner. Therefore, we propose a novel Selective Alignment Network for cross-domain pedestrian detection, which consists of three components: a Base Detector, an Image-Level Adaptation Network, and an Instance-Level Adaptation Network. The Image-Level Adaptation Network and Instance-Level Adaptation Network can be regarded as the global-level and local-level alignments, respectively. Similar to the Faster R-CNN, the Base Detector, which is composed of a Feature module, an RPN module and a Detection module, is used to infer a robust pedestrian detector with the annotated source data. Once obtaining the image description extracted by the Feature module, the Image-Level Adaptation Network is proposed to align the image description with an adversarial domain classifier. Given the candidate proposals generated by the RPN module, the Instance-Level Adaptation Network firstly clusters the source candidate proposals into several groups according to their visual features, and thus generates the pseudo label for each candidate proposal. After generating the pseudo labels, we align the source and target domains by maximizing and minimizing the discrepancy between the prediction of two classifiers iteratively. Extensive evaluations on several benchmarks demonstrate the effectiveness of the proposed approach for cross-domain pedestrian detection.
关键词	Proposals Feature extraction Detectors Visualization Training Image color analysis Adaptation models Cross-domain pedestrian detection instance-level adaptation network image-level adaptation network pedestrian detection
DOI	10.1109/TIP.2021.3049948
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018AAA0102205] ; National Natural Science Foundation of China[61902399] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[U1836220] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[61832002] ; National Natural Science Foundation of China[61720106006] ; Beijing Natural Science Foundation[L201001] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Key Research Program of Frontier Sciences, CAS
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000613403600005
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	目标检测、跟踪与识别
引用统计	被引频次：14[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/173211/43107
专题	多模态人工智能系统全国重点实验室_多媒体计算
通讯作者	Xu, Changsheng
作者单位	1.Hefei Univ Technol, Sch Comp Sci & Informat Engn, Hefei 230009, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Jiao, Yifan,Yao, Hantao,Xu, Changsheng. SAN: Selective Alignment Network for Cross-Domain Pedestrian Detection[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:2155-2167.
APA	Jiao, Yifan,Yao, Hantao,&Xu, Changsheng.(2021).SAN: Selective Alignment Network for Cross-Domain Pedestrian Detection.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,2155-2167.
MLA	Jiao, Yifan,et al."SAN: Selective Alignment Network for Cross-Domain Pedestrian Detection".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):2155-2167.