Detecting Small Objects Using a Channel-Aware Deconvolutional Network

doi:10.1109/TCSVT.2019.2906246

	Detecting Small Objects Using a Channel-Aware Deconvolutional Network
	Duan, Kaiwen 1,2; Du, Dawei 3; Qi, Honggang 1,2; Huang, Qingming 1,2,4
	2020-06-01
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
卷号	30 期号:6 页码:1639-1652
摘要	Detecting small objects is a challenging task due to their low resolution and noisy representation even using deep learning methods. In this paper, we propose a novel object detection method based on the channel-aware deconvolutional network (CADNet) for accurate small object detection. Specifically, we develop the channel-aware deconvolution (ChaDeConv) layer to exploit the correlations of feature maps in different channels across deeper layers, improving the recall rate of small objects at low additional computational costs. Following the ChaDeConv layer, the multiple region proposal sub-network (Multi-RPN) is employed to supervise and optimize multiple detection layers simultaneously to achieve better accuracy. The Multi-RPN module is only used in the training phase and does not increase the computation cost of the inference. In addition, we design a new anchor matching strategy based on the center point translation (CPTMatching) of anchors to select more extending anchors as positive samples in the training phase. The extensive experiments on the PASCAL VOC 2007/2012, MS COCO, and UAVDT datasets show that the proposed CADNet achieves state-of-the-art performance compared to the existing methods.
关键词	Object detection Feature extraction Training Birds Deconvolution Proposals Detectors Small object detection channel-aware deconvolution multi-RPN anchor matching
DOI	10.1109/TCSVT.2019.2906246
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61620106009] ; National Natural Science Foundation of China[U1636214] ; National Natural Science Foundation of China[61836002] ; National Natural Science Foundation of China[61771341] ; National Natural Science Foundation of China[61472388] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-SYS013]
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000543144200012
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：38[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/2XEOYT63/15203
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Qi, Honggang; Huang, Qingming
作者单位	1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 2.Univ Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 100190, Peoples R China 3.SUNY Albany, Dept Comp Sci, Albany, NY 12222 USA 4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Duan, Kaiwen,Du, Dawei,Qi, Honggang,et al. Detecting Small Objects Using a Channel-Aware Deconvolutional Network[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2020,30(6):1639-1652.
APA	Duan, Kaiwen,Du, Dawei,Qi, Honggang,&Huang, Qingming.(2020).Detecting Small Objects Using a Channel-Aware Deconvolutional Network.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,30(6),1639-1652.
MLA	Duan, Kaiwen,et al."Detecting Small Objects Using a Channel-Aware Deconvolutional Network".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 30.6(2020):1639-1652.