Location Sensitive Network for Human Instance Segmentation

doi:10.1109/TIP.2021.3107210

	Location Sensitive Network for Human Instance Segmentation
	Zhang, Xiangzhou 1; Ma, Bingpeng 2; Chang, Hong 2,3; Shan, Shiguang 3,4; Chen, Xilin 2,3
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2021
卷号	30 页码:7649-7662
关键词	Image segmentation Prototypes Heating systems Task analysis Semantics Feature extraction Detectors Human instance segmentation spatial invariance coordinates encoding points representation
ISSN号	1057-7149
DOI	10.1109/TIP.2021.3107210
英文摘要	Location is an important distinguishing information for instance segmentation. In this paper, we propose a novel model, called Location Sensitive Network (LSNet), for human instance segmentation. LSNet integrates instance-specific location information into one-stage segmentation framework. Specifically, in the segmentation branch, Pose Attention Module (PAM) encodes the location information into the attention regions through coordinates encoding. Based on the location information provided by PAM, the segmentation branch is able to effectively distinguish instances in feature-level. Moreover, we propose a combination operation named Keypoints Sensitive Combination (KSCom) to utilize the location information from multiple sampling points. These sampling points construct the points representation for instances via human keypoints and random points. Human keypoints provide the spatial locations and semantic information of the instances, and random points expand the receptive fields. Based on the points representation for each instance, KSCom effectively reduces the mis-classified pixels. Our method is validated by the experiments on public datasets. LSNet-5 achieves 56.2 mAP at 18.5 FPS on COCOPersons. Besides, the proposed method is significantly superior to its peers in the case of severe occlusion.
资助项目	National Key Research and Development Program of China[2017YFA0700800] ; Natural Science Foundation of China (NSFC)[61876171] ; Natural Science Foundation of China (NSFC)[61976203]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000693758500010
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17148]
专题	中国科学院计算技术研究所
通讯作者	Ma, Bingpeng
作者单位	1.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Chinese Acad Sci CAS, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Xiangzhou,Ma, Bingpeng,Chang, Hong,et al. Location Sensitive Network for Human Instance Segmentation[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2021,30:7649-7662.
APA	Zhang, Xiangzhou,Ma, Bingpeng,Chang, Hong,Shan, Shiguang,&Chen, Xilin.(2021).Location Sensitive Network for Human Instance Segmentation.IEEE TRANSACTIONS ON IMAGE PROCESSING,30,7649-7662.
MLA	Zhang, Xiangzhou,et al."Location Sensitive Network for Human Instance Segmentation".IEEE TRANSACTIONS ON IMAGE PROCESSING 30(2021):7649-7662.