CL2OD: Class-Incremental Continual Learning for Outdoor 3D Object Detection in Autonomous Driving

Xihao Wang, Xiangzhong Liu

Abstract: The classic learning paradigm of deep neural networks is becoming increasingly difficult to handle the evergrowing real-world traffic data in the intelligent transportation domain. To manage more complex and constantly growing traffic data, continual learning has attracted significant attention as a promising ability. This ability allows models to study new tasks sequentially while maintaining the performance of previously learned tasks. However, due to the characteristics of LiDAR data being different from the indoor point clouds, most existing research on continual learning has limited exploration of the outdoor 3D point cloud scenarios. The feasibility of directly applying continual learning techniques to real-world intelligent traffic scenarios remains unclear. To narrow down this gap, we propose a class-incremental continual learning strategy for LiDAR point cloud object detection via knowledge distillation. To enhance the adaptability of dynamic traffic scenarios, we further extract the equivariant features of the point cloud. In the experiment section, we evaluate our approach on the nuScenes dataset and achieve promising results. These findings demonstrate the effectiveness of our method and highlight its potential for advancing continual learning in autonomous driving applications.

External IDs:dblp:conf/ijcnn/WangL25