Accuracy Improvement of UNet Based on Dilated Convolution

Abstract

Abstract Though previous approach for the satellite image semantic segmentation task has already achieved reliable performance across some different benchmarks, there are still some limitations for the existing methods when faced with the scenarios of the high-resolution images. In this paper, we propose a powerful dilated convolution module and successfully apply it into our improved UNet network structure. The dilated convolution module can directly expand the receptive field of the network without reducing the resolution. Experiments on DeepGlobe Road Extraction Task have shown that the proposed method in this work can achieve the mIoU score of 63.72%, which significantly outperforms the original algorithm.