Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
This work addresses class imbalance in autonomous driving scenarios, which is an incremental improvement over existing methods.
The authors tackled severe class imbalance in 3D object detection for autonomous driving by designing a class-balanced sampling and augmentation strategy, achieving state-of-the-art performance on the nuScenes dataset and outperforming the PointPillars baseline by a large margin across all metrics.
This report presents our method which wins the nuScenes3D Detection Challenge [17] held in Workshop on Autonomous Driving(WAD, CVPR 2019). Generally, we utilize sparse 3D convolution to extract rich semantic features, which are then fed into a class-balanced multi-head network to perform 3D object detection. To handle the severe class imbalance problem inherent in the autonomous driving scenarios, we design a class-balanced sampling and augmentation strategy to generate a more balanced data distribution. Furthermore, we propose a balanced group-ing head to boost the performance for the categories withsimilar shapes. Based on the Challenge results, our methodoutperforms the PointPillars [14] baseline by a large mar-gin across all metrics, achieving state-of-the-art detection performance on the nuScenes dataset. Code will be released at CBGS.