Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- August 2019
- DOI:
- 10.48550/arXiv.1908.09492
- arXiv:
- arXiv:1908.09492
- Bibcode:
- 2019arXiv190809492Z
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- technical report