中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Decoupled R-CNN: Sensitivity-Specific Detector for Higher Accurate Localization

文献类型：期刊论文

作者Wang, Dong3; Shang, Kun1; Wu, Huaming3; Wang, Ce2,4
刊名IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
出版日期2022-09-01
卷号32期号:9页码:6324-6336
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
ISSN号1051-8215
DOI10.1109/TCSVT.2022.3167114
英文摘要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.
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
语种英语
WOS记录号WOS:000849300000049
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/19432]  
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.Chinese Acad Sci, Res Ctr Med AI, Shenzhen Inst Adv Technol, Shenzhen 518055, Peoples R China
2.Chinese Acad Sci, Suzhou Inst Intelligent Comp Technol, Suzhou 215123, Peoples R China
3.Tianjin Univ, Ctr Appl Math, Tianjin 300072, Peoples R China
4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, 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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。