Bootstrapping Autonomous Driving Radars with Self-Supervised Learning

TL;DR

This paper introduces a self-supervised learning framework for autonomous vehicle radars, enabling effective pre-training on unlabeled data to improve object detection accuracy in adverse weather conditions.

Contribution

It proposes a novel contrastive learning approach combining radar-to-radar and radar-to-vision losses for radar data representation learning.

Findings

Improves object detection mAP by 5.8% over supervised baselines

Leverages large unlabeled radar datasets effectively

Enhances radar perception robustness in bad weather

Abstract

The perception of autonomous vehicles using radars has attracted increased research interest due its ability to operate in fog and bad weather. However, training radar models is hindered by the cost and difficulty of annotating large-scale radar data. To overcome this bottleneck, we propose a self-supervised learning framework to leverage the large amount of unlabeled radar data to pre-train radar-only embeddings for self-driving perception tasks. The proposed method combines radar-to-radar and radar-to-vision contrastive losses to learn a general representation from unlabeled radar heatmaps paired with their corresponding camera images. When used for downstream object detection, we demonstrate that the proposed self-supervision framework can improve the accuracy of state-of-the-art supervised baselines by $5.8\%$ in mAP. Code is available at \url{https://github.com/yiduohao/Radical}.