现代电子技术2025，Vol.48Issue(6)：106-112,7.DOI:10.16652/j.issn.1004-373x.2025.06.017
基于Ghost卷积与自适应注意力的点云分类
Point cloud classification based on Ghost convolution and adaptive attention
舒密 1王占刚1
作者信息
- 1. 北京信息科技大学 信息与通信工程学院,北京 100011
- 折叠
摘要
Abstract
The point cloud Transformer network can exhibit remarkable feature learning capabilities by extracting local features of three-dimensional point clouds and employing multi-level self-attention mechanisms.However,the multi-level self-attention layer has high requirements on computing and memory resources,and the differentiation and correlation between levels and channels in feature fusion are not considered fully.In order to solve the above problems,a lightweight point cloud Transformer based on enhanced feature fusion(EFF-LPCT)is proposed.In the EFF-LPCT,the original network is reconstructed by means of one-dimensional Ghost convolution to reduce computational complexity and memory requirements.The adaptive branch weight is used to realize the multi-scale feature fusion between attention levels and multiple channel attention modules are used to enhance channel interaction information,so as to improve the model classification performance.The experimental results on the ModelNet40 datasets demonstrate that EFF-LPCT can realize 93.3%high accuracy while reducing the floating point computation amount of 1.11 GFLOPs and the parameter number of 0.86×106 compared to point cloud Transformer.关键词
点云分类/Transformer网络/Ghost卷积/特征增强融合模块/ECA通道注意力/特征学习Key words
point cloud classification/Transformer network/Ghost convolution/feature enhancement fusion module/ECA channel attention/feature learning分类
电子信息工程引用本文复制引用
舒密,王占刚..基于Ghost卷积与自适应注意力的点云分类[J].现代电子技术,2025,48(6):106-112,7.
