RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features

arXiv:2403.05061v1 Announce Type: new
Abstract: The inherent noisy and sparse characteristics of radar data pose challenges in finding effective representations for 3D object detection. In this paper, we propose RadarDistill, a novel knowledge distillation (KD) method, which can improve the representation of radar data by leveraging LiDAR data. RadarDistill successfully transfers desirable characteristics of LiDAR features into radar features using three key components: Cross-Modality Alignment (CMA), Activation-based Feature Distillation (AFD), and Proposal-based Feature Distillation (PFD). CMA enhances the density of …

3d object 3d object detection abstract arxiv boosting challenges cs.cv data detection distillation features knowledge lidar novel object paper performance radar representation type via