ShanghaiTech University Knowledge Management System
One Training for Multiple Deployments: Polar-based Adaptive BEV Perception for Autonomous Driving | |
2023 | |
Source Publication | PROCEEDINGS - IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION
![]() |
ISSN | 1050-4729 |
Volume | 2023-May |
Pages | 5602-5609 |
Status | 已发表 |
DOI | 10.1109/ICRA48891.2023.10161552 |
Abstract | Current on-board chips usually have different computing power, which means multiple training processes are needed for adapting the same learning-based algorithm to different chips, costing huge computing resources. The situation becomes even worse for 3D perception methods with large models. Previous vision-centric 3D perception approaches are trained with regular grid-represented feature maps of fixed resolutions, which is not applicable to adapt to other grid scales, limiting wider deployment. In this paper, we leverage the Polar representation when constructing the BEV feature map from images in order to achieve the goal of training once for multiple deployments. Specifically, the feature along rays in Polar space can be easily adaptively sampled and projected to the feature in Cartesian space with arbitrary resolutions. To further improve the adaptation capability, we make multi-scale contextual information interact with each other to enhance the feature representation. Experiments on a large-scale autonomous driving dataset show that our method outperforms others as for the good property of one training for multiple deployments. © 2023 IEEE. |
Keyword | Computing power Large dataset 'current 3D perception Autonomous driving Computing power Computing resource Feature map Large models Learning-based algorithms Regular grids Training process |
Conference Name | 2023 IEEE International Conference on Robotics and Automation, ICRA 2023 |
Conference Place | London, United kingdom |
Conference Date | May 29, 2023 - June 2, 2023 |
URL | 查看原文 |
Indexed By | EI |
Language | 英语 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
EI Accession Number | 20233514632065 |
EI Keywords | Autonomous vehicles |
EI Classification Number | 432 Highway Transportation ; 722.2 Computer Peripheral Equipment ; 722.4 Digital Computers and Systems ; 723 Computer Software, Data Handling and Applications ; 723.2 Data Processing and Image Processing ; 731.6 Robot Applications |
Original Document Type | Conference article (CA) |
Source Data | IEEE |
Document Type | 会议论文 |
Identifier | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/325842 |
Collection | 信息科学与技术学院 信息科学与技术学院_PI研究组_马月昕 |
Affiliation | 1.School of Information Science and Technology, ShanghaiTech University, Shanghai, China 2.Department of Computer Science and Engineering, Hong Kong University of Science and Technology 3.Department of Information Engineering, The Chinese University of Hong Kong |
First Author Affilication | School of Information Science and Technology |
First Signature Affilication | School of Information Science and Technology |
Recommended Citation GB/T 7714 | Huitong Yang,Xuyang Bai,Xinge Zhu,et al. One Training for Multiple Deployments: Polar-based Adaptive BEV Perception for Autonomous Driving[C]:Institute of Electrical and Electronics Engineers Inc.,2023:5602-5609. |
Files in This Item: | Download All | |||||
File Name/Size | DocType | Version | Access | License |
Edit Comment
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.