Figure 3
From: MFCA-Net: a deep learning method for semantic segmentation of remote sensing images
Visualization of the results of the Vaihingen testing set: (a) image (b) ground truth, (c) SegNet47, (d) U-Net26, (e) PSPNet48, (f) DANet49, (g) DeepLab V3+50, (h) A2-FPN51, and (i) Our proposed approach. (This figure was drawn by Visio 2021, which can be available at https://www.microsoftstore.com.cn/software/office/visio-standard-2021, The visualization was achieved in Visdom under the PyTorch framework. Vaihingen can be available at https://www.isprs.org/education/benchmarks/UrbanSemLab/2d-sem-label-vaihingen.aspx).
