Accurate and reliable 3D detection is vital for many applications including autonomous driving vehicles and service robots.
In this paper, we propose a method, named EqCo (Equivalent Rules for Contrastive Learning), to make self-supervised learning irrelevant to the number of negative samples in InfoNCE-based contrastive learning frameworks.
During training, to both satisfy the prior distribution of data and adapt to category characteristics, we present Center Weighting to adjust the category-specific prior distributions.
This report presents our method which wins the nuScenes3D Detection Challenge  held in Workshop on Autonomous Driving(WAD, CVPR 2019).
Ranked #176 on 3D Object Detection on nuScenes