# Large-scale Weakly Supervised Learning for Road Extraction from Satellite Imagery

arXiv: https://arxiv.org/abs/2309.07823 · HTML: https://mlsanity.com/paper/2309.07823/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 14 Sep 2023.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Rethinking Pre-training and Self-training](https://mlsanity.com/paper/2006.06882/) (2020)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images](https://mlsanity.com/paper/1805.06561/) (2018)
- [RoadTracer: Automatic Extraction of Road Networks from Aerial Images](https://mlsanity.com/paper/1802.03680/) (2018)
- [Beyond the Pixel-Wise Loss for Topology-Aware Delineation](https://mlsanity.com/paper/1712.02190/) (2017)
- [Leveraging Crowdsourced GPS Data for Road Extraction from Aerial Imagery](https://mlsanity.com/paper/1905.01447/) (2019)
- [Fully Convolutional Network for Automatic Road Extraction from Satellite Imagery](https://mlsanity.com/paper/1806.05182/) (2018)
- [NL-LinkNet: Toward Lighter but More Accurate Road Extraction with Non-Local Operations](https://mlsanity.com/paper/1908.08223/) (2019)
- [Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation](https://mlsanity.com/paper/2104.11176/) (2021)

## Abstract (arXiv)

Automatic road extraction from satellite imagery using deep learning is a viable alternative to traditional manual mapping. Therefore it has received considerable attention recently. However, most of the existing methods are supervised and require pixel-level labeling, which is tedious and error-prone. To make matters worse, the earth has a diverse range of terrain, vegetation, and man-made objects. It is well known that models trained in one area generalize poorly to other areas. Various shooting conditions such as light and angel, as well as different image processing techniques further complicate the issue. It is impractical to develop training data to cover all image styles. This paper proposes to leverage OpenStreetMap road data as weak labels and large scale satellite imagery to pre-train semantic segmentation models. Our extensive experimental results show that the prediction accuracy increases with the amount of the weakly labeled data, as well as the road density in the areas chosen for training. Using as much as 100 times more data than the widely used DeepGlobe road dataset, our model with the D-LinkNet architecture and the ResNet-50 backbone exceeds the top performer of the current DeepGlobe leaderboard. Furthermore, due to large-scale pre-training, our model generalizes much better than those trained with only the curated datasets, implying great application potential.