Recent advances in 3D object detection are made by developing the refinement stage for voxel-based Region Proposal Networks (RPN) to better strike the balance between accuracy and efficiency. A popular approach among state-of-the-art frameworks is to divide proposals, or Regions of Interest (ROI), into grids and extract features for each grid location before synthesizing them to form ROI features. While achieving impressive performances, such an approach involves several hand-crafted components (e.g. grid sampling, set abstraction) which requires expert knowledge to be tuned correctly. This paper proposes a data-driven approach to ROI feature computing named APRO3D-Net which consists of a voxel-based RPN and a refinement stage made of Vector Attention. Unlike the original multi-head attention, Vector Attention assigns different weights to different channels within a point feature, thus being able to capture a more sophisticated relation between pooled points and ROI. Our method achieves a competitive performance of 84.85 AP for class Car at moderate difficulty on validation set of KITTI and 47.03 mAP (average over 10 classes) on NuScenes while having the least parameters compared to closely related methods and attaining an inference speed at 15 FPS on NVIDIA V100 GPU. The code is released 1.1https://github.com/quan-dao/APRO3D-Net


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Attention-based Proposals Refinement for 3D Object Detection


    Contributors:


    Publication date :

    2022-06-05


    Size :

    2858881 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    LEVERAGING OBJECT PROPOSALS FOR OBJECT-LEVEL CHANGE DETECTION

    Takuma, Sugimoto / Kanji, Tanaka / Kousuke, Yamaguchi | British Library Conference Proceedings | 2018


    Leveraging Object Proposals for Object-Level Change Detection

    Takuma, Sugimoto / Kanji, Tanaka / Kousuke, Yamaguchi | IEEE | 2018


    Pose-RCNN: Joint object detection and pose estimation using 3D object proposals

    Braun, Markus / Qing Rao / Wang, Yikang et al. | IEEE | 2016


    RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement

    Shin, Kiwoo / Kwon, Youngwook Paul / Tomizuka, Masayoshi | IEEE | 2019