Exploring Semi-Supervised Learning for Online Mapping

TL;DR

This paper demonstrates that semi-supervised learning significantly improves online mapping accuracy in autonomous driving, reducing dependence on labelled data and enabling better generalization across different cities.

Contribution

It introduces a simple pseudo-label fusion method for SSL in online mapping and shows substantial performance gains with limited labelled data.

Findings

3.5x performance boost with 10% labelled data

Reduced domain gap from 5 to 0.5 mIoU in unseen city

Effective SSL method for online mapping tasks

Abstract

The ability to generate online maps using only onboard sensory information is crucial for enabling autonomous driving beyond well-mapped areas. Training models for this task -- predicting lane markers, road edges, and pedestrian crossings -- traditionally require extensive labelled data, which is expensive and labour-intensive to obtain. While semi-supervised learning (SSL) has shown promise in other domains, its potential for online mapping remains largely underexplored. In this work, we bridge this gap by demonstrating the effectiveness of SSL methods for online mapping. Furthermore, we introduce a simple yet effective method leveraging the inherent properties of online mapping by fusing the teacher's pseudo-labels from multiple samples, enhancing the reliability of self-supervised training. If 10% of the data has labels, our method to leverage unlabelled data achieves a 3.5x performance boost compared to only using the labelled data. This narrows the gap to a fully supervised model, using all labels, to just 3.5 mIoU. We also show strong generalization to unseen cities. Specifically, in Argoverse 2, when adapting to Pittsburgh, incorporating purely unlabelled target-domain data reduces the performance gap from 5 to 0.5 mIoU. These results highlight the potential of SSL as a powerful tool for solving the online mapping problem, significantly reducing reliance on labelled data.