NL-LinkNet: Toward Lighter but More Accurate Road Extraction with Non-Local Operations
arXiv:1908.08223
Abstract
Road extraction from very high resolution satellite (VHR) images is one of the most important topics in the field of remote sensing. In this paper, we propose an efficient Non-Local LinkNet with non-local blocks that can grasp relations between global features. This enables each spatial feature point to refer to all other contextual information and results in more accurate road segmentation. In detail, our single model without any post-processing like CRF refinement, performed better than any other published state-of-the-art ensemble model in the official DeepGlobe Challenge. Moreover, our NL-LinkNet beat the D-LinkNet, the winner of the DeepGlobe challenge, with 43 \% less parameters, less giga floating-point operations per seconds (GFLOPs) and shorter training convergence time. We also present empirical analyses on the proper usages of non-local blocks for the baseline model.
arXiv commentIEEE Geoscience and Remote Sensing Letters (2020, to appear)
References in corpus (6)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Road Extraction by Deep Residual U-Net
- DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images
- Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
- Residual Non-local Attention Networks for Image Restoration
- Parameter-Free Spatial Attention Network for Person Re-Identification