Few-Shot Online Learning for 3D Object Detection in Autonomous Driving

Dexin Yao, Binhong Liu, Rui Yang, Zhi Yan, Wenxing Fu, Tao Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

For autonomous driving, the performance of 3D object detection is limited by offline training, and these methods usually lack the adaption ability for long-term autonomy, which leads to significant performance degeneration across different scenarios, i.e. domain shift. This paper proposes a few-shot online learning method to transfer knowledge from 2D images to 3D point clouds. In particular, the point cloud clusters are automatically labeled by the 3D-2D projection and 3D object tracking, and the learning strategy allows the classifier to learn multiple classes with limited samples in a short period of time. The final 3D detection results are obtained from the fusion of the online learning 3D detector and an end-to-end 3D detector. Experimental results on the KITTI dataset demonstrate the effectiveness of our system compared to the baseline methods.

Original languageEnglish
Title of host publicationProceedings of 3rd 2023 International Conference on Autonomous Unmanned Systems (3rd ICAUS 2023) - Volume III
EditorsYi Qu, Mancang Gu, Yifeng Niu, Wenxing Fu
PublisherSpringer Science and Business Media Deutschland GmbH
Pages282-291
Number of pages10
ISBN (Print)9789819710867
DOIs
StatePublished - 2024
Event3rd International Conference on Autonomous Unmanned Systems, ICAUS 2023 - Nanjing, China
Duration: 9 Sep 202311 Sep 2023

Publication series

NameLecture Notes in Electrical Engineering
Volume1173 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference3rd International Conference on Autonomous Unmanned Systems, ICAUS 2023
Country/TerritoryChina
CityNanjing
Period9/09/2311/09/23

Keywords

  • 3D object detection
  • Autonomous Driving
  • Few-shot learning
  • Online learning

Fingerprint

Dive into the research topics of 'Few-Shot Online Learning for 3D Object Detection in Autonomous Driving'. Together they form a unique fingerprint.

Cite this