GA-NET: Global Attention Network for Point Cloud Semantic Segmentation

doi:10.1109/LSP.2021.3082851

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 > 机器人视觉团队

	GA-NET: Global Attention Network for Point Cloud Semantic Segmentation
	Deng, Shuang 1,2,3; Dong, Qiulei 1,2,3
刊名	IEEE SIGNAL PROCESSING LETTERS
	2021
卷号	28 页码:1300-1304
关键词	Three-dimensional displays Feature extraction Semantics Computational complexity Vegetation mapping Image segmentation Feeds 3D point cloud semantic segmentation global attention convolutional neural networks deep learning
ISSN号	1070-9908
DOI	10.1109/LSP.2021.3082851
通讯作者	Dong, Qiulei(qldong@nlpr.ia.ac.cn)
英文摘要	How to learn long-range dependencies from 3D point clouds is a challenging problem in 3D point cloud analysis. Addressing this problem, we propose a global attention network for point cloud semantic segmentation, named as GA-Net, consisting of a point-independent global attention module and a point-dependent global attention module for obtaining contextual information of 3D point clouds in this paper. The point-independent global attention module simply shares a global attention map for all 3D points. In the point-dependent global attention module, for each point, a novel random cross attention block using only two randomly sampled subsets is exploited to learn the contextual information of all the points. Additionally, we design a novel point-adaptive aggregation block to replace linear skip connection for aggregating more discriminate features. Extensive experimental results on three 3D public datasets demonstrate that our method outperforms state-of-the-art methods in most cases.
资助项目	National Natural Science Foundation of China[U1805264] ; National Natural Science Foundation of China[61991423] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32050100] ; Key Laboratory of Intelligent Infrared Perception, Chinese Academy of Sciences
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000670537600003
资助机构	National Natural Science Foundation of China ; Strategic Priority Research Program of the Chinese Academy of Sciences ; Key Laboratory of Intelligent Infrared Perception, Chinese Academy of Sciences
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/45240]
专题	自动化研究所_模式识别国家重点实验室_机器人视觉团队
通讯作者	Dong, Qiulei
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Deng, Shuang,Dong, Qiulei. GA-NET: Global Attention Network for Point Cloud Semantic Segmentation[J]. IEEE SIGNAL PROCESSING LETTERS,2021,28:1300-1304.
APA	Deng, Shuang,&Dong, Qiulei.(2021).GA-NET: Global Attention Network for Point Cloud Semantic Segmentation.IEEE SIGNAL PROCESSING LETTERS,28,1300-1304.
MLA	Deng, Shuang,et al."GA-NET: Global Attention Network for Point Cloud Semantic Segmentation".IEEE SIGNAL PROCESSING LETTERS 28(2021):1300-1304.