Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic Segmentation
This work addresses the problem of achieving both high accuracy and real-time inference in LiDAR semantic segmentation for autonomous driving, presenting an incremental improvement over existing methods.
The paper tackles the trade-off between accuracy and speed in LiDAR point cloud segmentation for autonomous driving by developing a 3D-to-BEV knowledge distillation method, resulting in over 5% improvement on the SemanticKITTI test set and over 15% for specific classes like motorcycle and person.
LiDAR point cloud segmentation is one of the most fundamental tasks for autonomous driving scene understanding. However, it is difficult for existing models to achieve both high inference speed and accuracy simultaneously. For example, voxel-based methods perform well in accuracy, while Bird's-Eye-View (BEV)-based methods can achieve real-time inference. To overcome this issue, we develop an effective 3D-to-BEV knowledge distillation method that transfers rich knowledge from 3D voxel-based models to BEV-based models. Our framework mainly consists of two modules: the voxel-to-pillar distillation module and the label-weight distillation module. Voxel-to-pillar distillation distills sparse 3D features to BEV features for middle layers to make the BEV-based model aware of more structural and geometric information. Label-weight distillation helps the model pay more attention to regions with more height information. Finally, we conduct experiments on the SemanticKITTI dataset and Paris-Lille-3D. The results on SemanticKITTI show more than 5% improvement on the test set, especially for classes such as motorcycle and person, with more than 15% improvement. The code can be accessed at https://github.com/fengjiang5/Knowledge-Distillation-from-Cylinder3D-to-PolarNet.