RSDet plus plus : Point-Based Modulated Loss for More Accurate Rotated Object Detection

doi:10.1109/TCSVT.2022.3186070

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能制造技术与系统研究中心 > 多维数据分析团队

	RSDet plus plus : Point-Based Modulated Loss for More Accurate Rotated Object Detection
	Qian, Wen 3,4; Yang, Xue 2; Peng, Silong 3,4; Zhang, Xiujuan 1; Yan, Junchi 2
刊名	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2022-11-01
卷号	32 期号:11 页码:7869-7879
关键词	Object detection Detectors Sensitivity Feature extraction Benchmark testing Training Measurement units Rotated object detection modulated loss point-based tiny objects
ISSN号	1051-8215
DOI	10.1109/TCSVT.2022.3186070
通讯作者	Peng, Silong(silong.peng@ia.ac.cn)
英文摘要	We classify the discontinuity of loss in both five-param and eight-param rotated object detection methods as rotation sensitivity error (RSE) which will result in performance degeneration. We introduce a novel modulated rotation loss to alleviate the problem and a rotation sensitivity detection network (RSDet) which consists of an eight-param single-stage rotated object detector and the modulated rotation loss. Our proposed RSDet has several advantages: 1) it reformulates the rotated object detection problem as predicting the corners of objects while most previous methods employ a five-param-based regression method with different measurement units. 2) modulated rotation loss achieves consistent improvement on both five-param and eight-param rotated object detection methods by solving the discontinuity of loss. To further improve the accuracy of our method on objects smaller than 10 pixels, we introduce a novel RSDet++ which consists of a point-based anchor-free rotated object detector and a modulated rotation loss. Extensive experiments demonstrate the effectiveness of both RSDet and RSDet++, which achieve competitive results on rotated object detection in the challenging benchmarks DOTA-v1.0, DOTA-v1.5, and DOTA-v2.0. We hope the proposed method can provide a new perspective for designing algorithms to solve rotated object detection and pay more attention to tiny objects. The codes and models are available at: https://github.com/yangxue0827/RotationDetection.
资助项目	Commercialization of Research Findings Fund of Inner Mongolia Autonomous Region[2020CG0075]
WOS关键词	TEXT DETECTION ; NETWORK ; REFINEMENT
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000876020600046
资助机构	Commercialization of Research Findings Fund of Inner Mongolia Autonomous Region
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50681]
专题	自动化研究所_智能制造技术与系统研究中心_多维数据分析团队
通讯作者	Peng, Silong
作者单位	1.Inner Mongolia Key Lab Mol Biol Featured Plants, Hohhot 010018, Peoples R China 2.Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Shanghai 200240, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Qian, Wen,Yang, Xue,Peng, Silong,et al. RSDet plus plus : Point-Based Modulated Loss for More Accurate Rotated Object Detection[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2022,32(11):7869-7879.
APA	Qian, Wen,Yang, Xue,Peng, Silong,Zhang, Xiujuan,&Yan, Junchi.(2022).RSDet plus plus : Point-Based Modulated Loss for More Accurate Rotated Object Detection.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,32(11),7869-7879.
MLA	Qian, Wen,et al."RSDet plus plus : Point-Based Modulated Loss for More Accurate Rotated Object Detection".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 32.11(2022):7869-7879.