Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection
Preprint
Abstract
Leveraging LiDAR-based detectors or real LiDAR point data to guide monocular 3D detection has brought significant improvement, e.g., Pseudo-LiDAR methods. However, the existing methods usually apply non-end-to-end training strategies and insufficiently leverage the LiDAR information, where the rich potential of the LiDAR data has not been well exploited. In this paper, we propose the Cross-Modality Knowledge Distillation (CMKD) network for monocular 3D detection to efficiently and directly transfer the knowledge from LiDAR modality to image modality on both features and responses. Moreover, we further extend CMKD as a semi-supervised training framework by distilling knowledge from large-scale unlabeled data and significantly boost the performance. Until submission, CMKD ranks $1^{st}$ among the monocular 3D detectors with publications on both KITTI $test$ set and Waymo $val$ set with significant performance gains compared to previous state-of-the-art methods.
Keywords
All Related Versions
- Version 1, 2022-11-14, ArXiv
- Published version: , 87.
This publication has 38 references indexed in Scilit:
- Lidar Point Cloud Guided Monocular 3D Object Detection2022
- P2V-RCNN: Point to Voxel Feature Learning for 3D Object Detection From Point CloudsIEEE Access, 2021
- MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection2020
- Monocular 3D Object Detection via Feature Domain Adaptation2020
- Frustum PointNets for 3D Object Detection from RGB-D Data2018
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection2018
- Deep Ordinal Regression Network for Monocular Depth Estimation2018
- Deep Residual Learning for Image Recognition2016
- Microsoft COCO: Common Objects in Context2014
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012