Knowledge distillation has recently been proven to be effective for model compression and acceleration of point cloud-based 3D object detection. However, the complementary network pruning is often overlooked during knowledge distillation. In this paper, we propose a pre-pruned distillation framework that combines network pruning and knowledge distillation to better transfer knowledge from the teacher to the student. To maintain the feature consistency between the student and the teacher, we train a teacher model and then generate a compact student model by structural channel pruning. Then, we employ multi-source knowledge distillation to transfer both mid-level and high-level information to the student model. Additionally, to improve the object detection performance of the student model, we propose a soft pivotal position selection mask to emphasize the features of the foreground regions during distillation. We conduct experiments on both pillarand voxel-based 3D object detectors on the Waymo datasets, demonstrating the effectiveness of our approach in compressing point cloud-based 3D detectors.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pre-pruned Distillation for Point Cloud-based 3D Object Detection


    Contributors:
    Li, Fuyang (author) / Min, Chen (author) / Xiao, Liang (author) / Zhao, Dawei (author) / Si, Shubin (author) / Xue, Hanzhang (author) / Nie, Yiming (author) / Dai, Bin (author)


    Publication date :

    2024-06-02


    Size :

    1519633 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Local pruning global pruned network under knowledge distillation

    Luo, Hanyi / Tang, Hao / Zhan, Kun | British Library Conference Proceedings | 2021


    Fast interpolation for line-pruned images

    Le, A.V. / Kim, H.-m. / Won, C.S. | British Library Online Contents | 2011


    Localization Distillation for Object Detection

    Zheng, Zhaohui / Ye, Rongguang / Hou, Qibin et al. | ArXiv | 2022

    Free access

    Covariance based point cloud descriptors for object detection and recognition

    Fehr, Duc / Beksi, William J. / Zermas, Dimitris et al. | British Library Online Contents | 2016


    PV-EncoNet: Fast Object Detection Based on Colored Point Cloud

    Ouyang, Zhenchao / Dong, Xiaoyun / Cui, Jiahe et al. | IEEE | 2022