TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

TL;DR

This paper introduces TopoAL, an adversarial learning method with a multi-scale discriminator for improved topology-aware road segmentation from aerial images, outperforming existing methods on a challenging dataset.

Contribution

It presents a novel adversarial learning framework with a scale-aware discriminator that better captures local errors, enhancing road network connectivity in segmentation.

Findings

Outperforms state-of-the-art methods on RoadTracer dataset

Uses a multi-scale discriminator for topology preservation

Improves binary road masks' global connectivity

Abstract

Most state-of-the-art approaches to road extraction from aerial images rely on a CNN trained to label road pixels as foreground and remainder of the image as background. The CNN is usually trained by minimizing pixel-wise losses, which is less than ideal to produce binary masks that preserve the road network's global connectivity. To address this issue, we introduce an Adversarial Learning (AL) strategy tailored for our purposes. A naive one would treat the segmentation network as a generator and would feed its output along with ground-truth segmentations to a discriminator. It would then train the generator and discriminator jointly. We will show that this is not enough because it does not capture the fact that most errors are local and need to be treated as such. Instead, we use a more sophisticated discriminator that returns a label pyramid describing what portions of the road network are correct at several different scales. This discriminator and the structured labels it returns are what gives our approach its edge and we will show that it outperforms state-of-the-art ones on the challenging RoadTracer dataset.