Self-Supervised Learning for Point-Cloud Classification by a Multigrid Autoencoder
Author:
Zhai Ruifeng,Song Junfeng,Hou Shuzhao,Gao Fengli,Li Xueyan
Abstract
It has become routine to directly process point clouds using a combination of shared multilayer perceptrons and aggregate functions. However, this practice has difficulty capturing the local information of point clouds, leading to information loss. Nevertheless, several recent works have proposed models that establish point-to-point relationships based on this procedure. However, to address the information loss, in this study we use self-supervised methods to enhance the network’s understanding of point clouds. Our proposed multigrid autoencoder (MA) constrains the encoder part of the classification network so that it gains an understanding of the point cloud as it reconstructs it. With the help of self-supervised learning, we find the original network improves performance. We validate our model on PointNet++, and the experimental results show that our method improves overall classification accuracy by 2.0% and 4.7% with ModelNet40 and ScanObjectNN datasets, respectively.
Funder
National Key Research and Development Program of China
National Natural Science Foundation of China
Major Science and Technology Special Project Subjects of Jilin Province and Changchun City
Major Scientific and Technological Program of Jilin Province
Program for Science and Technology Innovative Research Team of Jilin University
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献