UFO-Net: A Linear Attention-Based Network for Point Cloud Classification

doi:10.3390/s23125512

科研成果详情

题名	UFO-Net: A Linear Attention-Based Network for Point Cloud Classification
作者	He，Sheng 1; Guo，Peiyao 1; Tang，Zeyu 3; Guo，Dongxin 1; Wan，Lingyu 1; Yao，Huilu 1,2
发表日期	2023-06-01
发表期刊	Sensors
ISSN/eISSN	1424-8220
卷号	23 期号:12
摘要	Three-dimensional point cloud classification tasks have been a hot topic in recent years. Most existing point cloud processing frameworks lack context-aware features due to the deficiency of sufficient local feature extraction information. Therefore, we designed an augmented sampling and grouping module to efficiently obtain fine-grained features from the original point cloud. In particular, this method strengthens the domain near each centroid and makes reasonable use of the local mean and global standard deviation to extract point cloud’s local and global features. In addition to this, inspired by the transformer structure UFO-ViT in 2D vision tasks, we first tried to use a linearly normalized attention mechanism in point cloud processing tasks, investigating a novel transformer-based point cloud classification architecture UFO-Net. An effective local feature learning module was adopted as a bridging technique to connect different feature extraction modules. Importantly, UFO-Net employs multiple stacked blocks to better capture feature representation of the point cloud. Extensive ablation experiments on public datasets show that this method outperforms other state-of-the-art methods. For instance, our network performed with 93.7% overall accuracy on the ModelNet40 dataset, which is 0.5% higher than PCT. Our network also achieved 83.8% overall accuracy on the ScanObjectNN dataset, which is 3.8% better than PCT.
关键词	augmented sampling and grouping classification point cloud transformer-based UFO attention
DOI	10.3390/s23125512
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-85164036445
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/11580
专题	北师香港浸会大学
通讯作者	Yao，Huilu
作者单位	1.School of Physical Science & Technology,Guangxi University,Nanning,530004,China 2.School of Electrical Engineering,Guangxi University,Nanning,530004,China 3.Faculty of Science and Technology,Beijing Normal University-Hong Kong Baptist University United International College,Zhuhai,519087,China
推荐引用方式 GB/T 7714	He，Sheng,Guo，Peiyao,Tang，Zeyuet al. UFO-Net: A Linear Attention-Based Network for Point Cloud Classification[J]. Sensors, 2023, 23(12).
APA	He，Sheng, Guo，Peiyao, Tang，Zeyu, Guo，Dongxin, Wan，Lingyu, & Yao，Huilu. (2023). UFO-Net: A Linear Attention-Based Network for Point Cloud Classification. Sensors, 23(12).
MLA	He，Sheng,et al."UFO-Net: A Linear Attention-Based Network for Point Cloud Classification". Sensors 23.12(2023).