4.7 Article

TNPC: Transformer-based network for cloud classification☆

期刊

EXPERT SYSTEMS WITH APPLICATIONS
卷 239, 期 -, 页码 -

出版社

PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2023.122438

关键词

Point cloud classification; Transformer; Deep learning

向作者/读者索取更多资源

This paper proposes a novel hierarchical local-global framework based on the Transformer network for point cloud classification, named TNPC. The framework reduces computation and memory consumption by implementing downsampling operation and utilizing parallel branches. Experimental results show that the proposed method achieves state-of-the-art performance in terms of classification accuracy and efficiency.
Point cloud classification has emerged as a vital research area in several emerging applications, including robotics and autonomous driving. However, discriminative feature learning has long been a challenging issue owing to the irregularity and disorder of point clouds. Recently, although Transformer-based methods can achieve high accuracy in point cloud learning, plenty of Transformer layers bring huge computation and memory consumption. This paper presents a novel hierarchical local-global framework based on Transformer network for point clouds, named TNPC. TNPC contains two serial Stages implementing downsampling operation, and each Stage is composed of a local feature extracting (LFE) block and a global feature extracting (GFE) block, which can reduce computation and memory consumption obviously. LFE block consists of two parallel branches, namely Transformer branch and shared multilayer perceptron (SMLP) branch, which are designed to learn relevant feature of any two points and local high-dimensional semantic features of each point between sampling centroid and its neighborhoods, respectively. The proposed two parallel branches not only improve the feature extraction effect, but also reduce the computation and memory consumption. GFE block consists of a center point contact (CPC) module and a global point cloud transformer layer (PCTL) module, which can improve the effect of global features extracting without adding the number of parameters and computation. The performance of our method is validated experimentally on ModelNet40 and ScanObjectNN datasets. Our method improves the mean accuracy on each category (mAcc) to 91.6% and 79.8% on the ModelNet40 dataset and ScanObjectNN dataset, respectively. In terms of efficiency, our method leads to a significant reduction, with only 4.73MB parameters and only 1.91GB floating-point operations (FLOPs). Experimental results demonstrate that the proposed method achieves state-of-the-art performance on classification accuracy and efficiency.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据