Decoupled R-CNN: Sensitivity-Specific Detector for Higher Accurate Localization

doi:10.1109/TCSVT.2022.3167114

	Decoupled R-CNN: Sensitivity-Specific Detector for Higher Accurate Localization
	Wang, Dong 1; Shang, Kun 2; Wu, Huaming 1; Wang, Ce 3,4
	2022-09-01
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
卷号	32 期号:9 页码:6324-6336
摘要	Object detection, as a fundamental problem in computer vision, has been widely used in many industrial applications, such as intelligent manufacturing and intelligent video surveillance. In this work, we find that classification and regression have different sensitivities to the object translation, from the investigation about the availability of highly overlapping proposals. More specifically, the regressor head has intrinsic characteristics of higher sensitivity to translation than the classifier. Based on it, we propose a decoupled sampling strategy for a deep detector, named Decoupled R-CNN, to decouple the proposals sampling for the two tasks, which induces two sensitivity-specific heads. Furthermore, we adopt the cascaded structure for the single regressor head of Decoupled R-CNN, which is an extremely simple but highly effective way of improving the performance of object detection. Extensive empirical analyses using real-world datasets demonstrate the value of the proposed method when compared with the state-of-the-art models. The reproducing code is available at https://github.com/shouwangzhe134/Decoupled-R-CNN.
关键词	Proposals Detectors Task analysis Sensitivity Object detection Training Feature extraction Object detection R-CNN two-stage detection decoupled sampling strategy decoupled R-CNN
DOI	10.1109/TCSVT.2022.3167114
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[12001180] ; National Natural Science Foundation of China[62071327] ; National Natural Science Foundation of China[61801325]
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000849300000049
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：13[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19433
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Shang, Kun
作者单位	1.Tianjin Univ, Ctr Appl Math, Tianjin 300072, Peoples R China 2.Chinese Acad Sci, Res Ctr Med AI, Shenzhen Inst Adv Technol, Shenzhen 518055, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Suzhou Inst Intelligent Comp Technol, Suzhou 215123, Peoples R China
推荐引用方式 GB/T 7714	Wang, Dong,Shang, Kun,Wu, Huaming,et al. Decoupled R-CNN: Sensitivity-Specific Detector for Higher Accurate Localization[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2022,32(9):6324-6336.
APA	Wang, Dong,Shang, Kun,Wu, Huaming,&Wang, Ce.(2022).Decoupled R-CNN: Sensitivity-Specific Detector for Higher Accurate Localization.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,32(9),6324-6336.
MLA	Wang, Dong,et al."Decoupled R-CNN: Sensitivity-Specific Detector for Higher Accurate Localization".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 32.9(2022):6324-6336.