FNE-PCT:用于三维分类的高效变压器网络

Ming Han, J. Sha, Yanheng Wang, C. Ma, Xiang Zhang
{"title":"FNE-PCT:用于三维分类的高效变压器网络","authors":"Ming Han, J. Sha, Yanheng Wang, C. Ma, Xiang Zhang","doi":"10.1109/ICMA54519.2022.9856260","DOIUrl":null,"url":null,"abstract":"Detection or classification directly from 3D point clouds has received increasing attention in recent years. Transformer is more suitable for processing point cloud data than convolutional neural networks because of its inherent permutation invariance in processing sequences. However, common sampling strategies increase the training time of the model based on Transformer, such as Point Cloud Transformer (PCT). Aiming at the problem of slow inference speed of PCT, we propose a network structure named Fast Neighbor Embedding Point Cloud Transformer (FNE-PCT) in this paper. Instead of farthest point sample (FPS) and nearest neighbor search in PCT, FNE-PCT uses a fast neighbor embedding module to improve the inference speed and a residual self-attention encoding module to enhance the expression ability. Extensive experiments based on 3D object classification show that our FNE-PCT outperforms other excellent algorithms such as PointNet, PointNet++ and PointCNN. Our FNE-PCT achieves 92.6% accuracy on ModelNet40, which is on the same level as PCT. Meanwhile the speed is boosted up 29.2%, 43.6% and 52.9% than PCT respectively on ModelNet10, ModelNet40 and ShapeNetParts datasets.","PeriodicalId":120073,"journal":{"name":"2022 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"FNE-PCT: An Efficient Transformer Network for 3D Classification\",\"authors\":\"Ming Han, J. Sha, Yanheng Wang, C. Ma, Xiang Zhang\",\"doi\":\"10.1109/ICMA54519.2022.9856260\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Detection or classification directly from 3D point clouds has received increasing attention in recent years. Transformer is more suitable for processing point cloud data than convolutional neural networks because of its inherent permutation invariance in processing sequences. However, common sampling strategies increase the training time of the model based on Transformer, such as Point Cloud Transformer (PCT). Aiming at the problem of slow inference speed of PCT, we propose a network structure named Fast Neighbor Embedding Point Cloud Transformer (FNE-PCT) in this paper. Instead of farthest point sample (FPS) and nearest neighbor search in PCT, FNE-PCT uses a fast neighbor embedding module to improve the inference speed and a residual self-attention encoding module to enhance the expression ability. Extensive experiments based on 3D object classification show that our FNE-PCT outperforms other excellent algorithms such as PointNet, PointNet++ and PointCNN. Our FNE-PCT achieves 92.6% accuracy on ModelNet40, which is on the same level as PCT. Meanwhile the speed is boosted up 29.2%, 43.6% and 52.9% than PCT respectively on ModelNet10, ModelNet40 and ShapeNetParts datasets.\",\"PeriodicalId\":120073,\"journal\":{\"name\":\"2022 IEEE International Conference on Mechatronics and Automation (ICMA)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-08-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE International Conference on Mechatronics and Automation (ICMA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICMA54519.2022.9856260\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Mechatronics and Automation (ICMA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICMA54519.2022.9856260","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

近年来,直接从三维点云中进行检测或分类越来越受到人们的关注。变压器在处理序列上具有排列不变性,因此比卷积神经网络更适合处理点云数据。然而,常用的基于Transformer的采样策略,如点云变压器(PCT),会增加模型的训练时间。针对PCT推理速度慢的问题,本文提出了一种快速邻居嵌入点云变压器(FNE-PCT)网络结构。FNE-PCT采用快速邻居嵌入模块提高推理速度,残差自关注编码模块增强表达能力,而不是采用PCT中的最远点样本(FPS)和最近邻搜索。基于3D目标分类的大量实验表明,我们的FNE-PCT优于PointNet、pointnet++和PointCNN等其他优秀算法。我们的FNE-PCT在ModelNet40上的准确率达到了92.6%,与PCT处于同一水平,同时在ModelNet10、ModelNet40和ShapeNetParts数据集上的速度分别比PCT提高了29.2%、43.6%和52.9%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
FNE-PCT: An Efficient Transformer Network for 3D Classification
Detection or classification directly from 3D point clouds has received increasing attention in recent years. Transformer is more suitable for processing point cloud data than convolutional neural networks because of its inherent permutation invariance in processing sequences. However, common sampling strategies increase the training time of the model based on Transformer, such as Point Cloud Transformer (PCT). Aiming at the problem of slow inference speed of PCT, we propose a network structure named Fast Neighbor Embedding Point Cloud Transformer (FNE-PCT) in this paper. Instead of farthest point sample (FPS) and nearest neighbor search in PCT, FNE-PCT uses a fast neighbor embedding module to improve the inference speed and a residual self-attention encoding module to enhance the expression ability. Extensive experiments based on 3D object classification show that our FNE-PCT outperforms other excellent algorithms such as PointNet, PointNet++ and PointCNN. Our FNE-PCT achieves 92.6% accuracy on ModelNet40, which is on the same level as PCT. Meanwhile the speed is boosted up 29.2%, 43.6% and 52.9% than PCT respectively on ModelNet10, ModelNet40 and ShapeNetParts datasets.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信