Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

26 Aug 2019  ·  Benjin Zhu, Zhengkai Jiang, Xiangxin Zhou, Zeming Li, Gang Yu ·

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.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Object Detection nuScenes MEGVII NDS 0.63.3 # 199
mAP 0.528 # 79

Methods