D2S: Towards Efficient Sparse 3D Object Detection via Dense to Sparse Knowledge Distillation

LiDAR-based 3D object detection is widely used in high-level autonomous driving schemes. However, the cumbersome modules in most 3D detectors lead to substantial computational overhead. Despite knowledge distillation (KD) is an effective approach for compressing models, previous methods cannot be extended to the dense-to-sparse paradigm. To this end, we propose a simple yet effective Dense to Sparse Knowledge Distillation (D2S) framework for accelerating 3D detectors. Firstly, to compensate for the difference in predicted location between dense and sparse detectors, we introduce a lightweight feature diffusion (FeaD) module for spreading important features. Secondly, to achieve high performance, we propose a dual-stream distillation scheme to transfer knowledge. In this scheme, we align both of the feature and category prediction between distillation pairs at important positions. Extensive experiments on KITTI and Waymo Open Dataset demonstrate the effectiveness of our method. For example, on KITTI dataset, the sparse detector we obtained surpasses VoxelNeXt with around 2.0× fewer parameters and 1.6× fewer FLOPs.