Knowledge Commons of Institute of Automation,CAS
Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space | |
Yahui Liu![]() ![]() ![]() ![]() | |
发表期刊 | IEEE/CAA Journal of Automatica Sinica
![]() |
ISSN | 2329-9266 |
2024 | |
卷号 | 11期号:1页码:231-239 |
通讯作者 | Lv, Yisheng(yisheng.lv@ia.ac.cn) |
摘要 | Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention, but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space (content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectNN. Source code of this paper is available at https://github.com/yahuiliu99/PointConT. |
关键词 | Content-based Transformer deep learning feature aggregator local attention point cloud classification |
DOI | 10.1109/JAS.2023.123432 |
关键词[WOS] | NETWORK |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China |
项目资助者 | National Natural Science Foundation of China |
WOS研究方向 | Automation & Control Systems |
WOS类目 | Automation & Control Systems |
WOS记录号 | WOS:001165394200015 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
七大方向——子方向分类 | 人工智能+交通 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/54506 |
专题 | 学术期刊_IEEE/CAA Journal of Automatica Sinica |
作者单位 | Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China |
推荐引用方式 GB/T 7714 | Yahui Liu,Bin Tian,Yisheng Lv,et al. Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space[J]. IEEE/CAA Journal of Automatica Sinica,2024,11(1):231-239. |
APA | Yahui Liu,Bin Tian,Yisheng Lv,Lingxi Li,&Fei-Yue Wang.(2024).Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space.IEEE/CAA Journal of Automatica Sinica,11(1),231-239. |
MLA | Yahui Liu,et al."Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space".IEEE/CAA Journal of Automatica Sinica 11.1(2024):231-239. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
JAS-2022-1385.pdf(8541KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论