Neighborhood Attention Makes the Encoder of ResUNet Stronger for Accurate Road Extraction

Abstract

In the domain of remote sensing image interpretation, road extraction from high-resolution aerial imagery has already been a hot research topic. Although deep CNNs have presented excellent results for semantic segmentation, the efficiency and capabilities of vision transformers (ViTs) are yet to be fully researched. As such, for accurate road extraction, a deep semantic segmentation neural network that utilizes the abilities of residual learning, heterogeneous convolutions (HetConvs), UNet, and ViTs, which is called ResUNetFormer, is proposed in this letter. The developed ResUNetFormer is evaluated on various cutting-edge deep learning-based road extraction techniques on the public Massachusetts road dataset. Statistical and visual results demonstrate the superiority of the ResUNetFormer over the state-of-the-art CNNs and ViTs for segmentation. The code will be made available publicly at https://github.com/aj1365/ResUNetFormer.