Structure Aware and Class Balanced 3D Object Detection on nuScenes Dataset

TL;DR

This paper improves 3D object detection on the nuScenes dataset by integrating a structure-aware auxiliary network that enhances localization accuracy without increasing inference complexity.

Contribution

It introduces a detachable auxiliary network utilizing structure information of 3D point clouds, jointly optimized with supervisions for better localization.

Findings

Enhanced localization accuracy demonstrated on nuScenes dataset.

Auxiliary network improves detection precision without extra inference cost.

Effective handling of class imbalance in 3D object detection.

Abstract

3-D object detection is pivotal for autonomous driving. Point cloud based methods have become increasingly popular for 3-D object detection, owing to their accurate depth information. NuTonomy's nuScenes dataset greatly extends commonly used datasets such as KITTI in size, sensor modalities, categories, and annotation numbers. However, it suffers from severe class imbalance. The Class-balanced Grouping and Sampling paper addresses this issue and suggests augmentation and sampling strategy. However, the localization precision of this model is affected by the loss of spatial information in the downscaled feature maps. We propose to enhance the performance of the CBGS model by designing an auxiliary network, that makes full use of the structure information of the 3D point cloud, in order to improve the localization accuracy. The detachable auxiliary network is jointly optimized by two point-level supervisions, namely foreground segmentation and center estimation. The auxiliary network does not introduce any extra computation during inference, since it can be detached at test time.