HAPGN: Hierarchical Attentive Pooling Graph Network for Point Cloud Segmentation

doi:10.1109/TMM.2020.3009499

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	HAPGN: Hierarchical Attentive Pooling Graph Network for Point Cloud Segmentation
	Chen, Chaofan 1; Qian, Shengsheng 2,3; Fang, Quan 2,3; Xu, Changsheng 2,3,4
刊名	IEEE TRANSACTIONS ON MULTIMEDIA
	2021
卷号	23 页码:2335-2346
关键词	Three-dimensional displays Feature extraction Task analysis Layout Logic gates Machine learning Two dimensional displays Point cloud segmentation hierarchical graph pooling gated graph attention network
ISSN号	1520-9210
DOI	10.1109/TMM.2020.3009499
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
英文摘要	Among different 3D data representations, point cloud stands out for its efficiency and flexibility. Hence, many researchers have been involved in the point cloud analysis recently. Existing approaches for point cloud segmentation task typically suffer from two limitations: 1) They usually treat different neighbor points as equals which cannot characterize the correlation between the center point and its neighborhoods well. Moreover, different parts may have different local structures for a point cloud, but they just learn a single representation space which is not sufficient and stable. 2) They often capture hierarchical information by heuristic sampling approaches which cannot reveal the spatial relationships of points well to learn global features. To overcome these limitations, we propose a novel hierarchical attentive pooling graph network (HAPGN) which utilizes the gated graph attention network (GGAN) and hierarchical graph pooling module (HiGPool) as building blocks for point cloud segmentation. Specifically, GGAN can highlight not only the importance of different neighbor points but also the importance of different representation spaces to enhance the local feature extraction. HiGPool is a novel pooling module that can capture the spatial layouts of points to learn the hierarchical features adequately. Experimental results on the ShapeNet part dataset and S3DIS dataset show that HAPGN can achieve superior performance over the state-of-the-art segmentation approaches. Furthermore, we also combine our proposed HiGPool with some recent approaches for point cloud classification and achieve better results on the ModelNet40 dataset.
资助项目	National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61532009] ; National Natural Science Foundation of China[61720106006] ; National Natural Science Foundation of China[61572503] ; National Natural Science Foundation of China[61802405] ; National Natural Science Foundation of China[61872424] ; National Natural Science Foundation of China[61702509] ; National Natural Science Foundation of China[61832002] ; National Natural Science Foundation of China[61936005] ; National Natural Science Foundation of China[U1705262] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039] ; K. C. Wong Education Foundation
WOS研究方向	Computer Science ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000679533800014
资助机构	National Natural Science Foundation of China ; Key Research Program of Frontier Sciences, CAS ; K. C. Wong Education Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/45593]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者	Xu, Changsheng
作者单位	1.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Peng Cheng Lab, Shenzhen 518066, Peoples R China
推荐引用方式 GB/T 7714	Chen, Chaofan,Qian, Shengsheng,Fang, Quan,et al. HAPGN: Hierarchical Attentive Pooling Graph Network for Point Cloud Segmentation[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2021,23:2335-2346.
APA	Chen, Chaofan,Qian, Shengsheng,Fang, Quan,&Xu, Changsheng.(2021).HAPGN: Hierarchical Attentive Pooling Graph Network for Point Cloud Segmentation.IEEE TRANSACTIONS ON MULTIMEDIA,23,2335-2346.
MLA	Chen, Chaofan,et al."HAPGN: Hierarchical Attentive Pooling Graph Network for Point Cloud Segmentation".IEEE TRANSACTIONS ON MULTIMEDIA 23(2021):2335-2346.