Global Patch Cross-Attention for Point Cloud Analysis
文献类型：会议论文
| 作者 | Tao ML(陶满礼)1,2 ; Zhao CY(赵朝阳)1; Wang JQ(王金桥)1,2; Tang M(唐明)1,2
|
| 出版日期 | 2022-10 |
| 会议日期 | 2022.11.4-2022.11.7 |
| 会议地点 | 深圳 |
| 关键词 | Global patch · Cross-attention · Contextual description · Point cloud analysis |
| 卷号 | 3 |
| DOI | https://doi.org/10.1007/978-3-031-18913-5_8 |
| 页码 | 96-111 |
| 英文摘要 | Despite the great achievement on 3D point cloud analysis with deep learning methods, the insufficiency of contextual semantic description, and misidentification of confusing objects remain tricky
problems. To address these challenges, we propose a novel approach,
Global Patch Cross-Attention Network (GPCAN), to learn more discriminative point cloud features effectively. Specifically, a global patch
construction module is developed to generate global patches which share
holistic shape similarity but hold diversity in local structure. Then the
local features are extracted from both the original point cloud and these
global patches. Further, a transformer-style cross-attention module is
designed to model cross-object relations, which are all point-pair attentions between the original point cloud and each global patch, for learning the context-dependent features of each global patch. In this way, our
method can integrate the features of original point cloud with both the
local features and global contexts in each global patch for enhancing the
discriminative power of the model. Extensive experiments on challenging point cloud classification and part segmentation benchmarks verify
that our GPCAN achieves the state-of-the-arts on both synthetic and
real-world datasets. |
| 源文献作者 | Shiqi Yu, Zhaoxiang Zhang, Pong C. Yuen, Junwei Han, Tieniu Tan, Yike Guo, Jianhuang Lai, Jianguo Zhang |
| 会议录 | 5th Chinese Conference, PRCV 2022, Shenzhen, China, November 4–7, 2022, Proceedings, Part III
 |
| 会议录出版者 | Springer |
| 会议录出版地 | Cham |
| 语种 | 英语 |
| URL标识 | 查看原文 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/56736]  |
| 专题 | 紫东太初大模型研究中心 |
| 通讯作者 | Tao ML(陶满礼) |
| 作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 |
| 推荐引用方式 GB/T 7714 | Tao ML,Zhao CY,Wang JQ,et al. Global Patch Cross-Attention for Point Cloud Analysis[C]. 见:. 深圳. 2022.11.4-2022.11.7. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。