Resolving Class Imbalance for LiDAR-based Object Detector by Dynamic Weight Average and Contextual Ground Truth Sampling

Daeun Lee, Jinkyu Kim

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    6 Citations (Scopus)

    Abstract

    An autonomous driving system requires a 3D object detector, which must perceive all present road agents reliably to navigate an environment safely. However, real-world driving datasets often suffer from the problem of data imbalance, which causes difficulties in training a model that works well across all classes, resulting in an undesired imbalanced sub-optimal performance. In this work, we propose a method to address this data imbalance problem. Our method consists of two main components: (i) a LiDAR-based 3D object detector with per-class multiple detection heads where losses from each head are modified by dynamic weight average to be balanced. (ii) Contextual ground truth (GT) sampling, where we improve conventional GT sampling techniques by leveraging semantic information to augment point cloud with sampled ground truth GT objects. Our experiment with KITTI and nuScenes datasets confirms our proposed method's effectiveness in dealing with the data imbalance problem, producing better detection accuracy compared to existing approaches.

    Original languageEnglish
    Title of host publicationProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages682-691
    Number of pages10
    ISBN (Electronic)9781665493468
    DOIs
    Publication statusPublished - 2023
    Event23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023 - Waikoloa, United States
    Duration: 2023 Jan 32023 Jan 7

    Publication series

    NameProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023

    Conference

    Conference23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023
    Country/TerritoryUnited States
    CityWaikoloa
    Period23/1/323/1/7

    Bibliographical note

    Funding Information:
    Acknowledgements. This work was supported by the grant from Autonomous Driving Center at Hyundai Motor Company’s R&D Division and the grant by ITRC(Information Technology Research Center) support program (IITP-2022-RS-2022-00156295). We thank Jaewoo Cho, Nokyung Park, and Jongwon Park for their helpful comments.

    Publisher Copyright:
    © 2023 IEEE.

    Keywords

    • Algorithms: Image recognition and understanding (object detection, categorization, segmentation)
    • Robotics

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Science Applications
    • Computer Vision and Pattern Recognition

    Fingerprint

    Dive into the research topics of 'Resolving Class Imbalance for LiDAR-based Object Detector by Dynamic Weight Average and Contextual Ground Truth Sampling'. Together they form a unique fingerprint.

    Cite this