jiankun-chen/building-semantic-segmentation-of-insar-images

We apply some state-of-the-art semantic segmentation methods to InSAR image building segmentation, directly. They are Unet, SegNet, RefineNet, PSPNet, and Deeplab v3+. These segmentation patterns are regarded as the comparative results with CVCMFFNet, which links to https://github.com/Jiankun-chen/CVCMFFNet-master

building-semantic-segmentation-of-insar-images's Issues

SARMV3D dataset

Hello, Mr. Chen. I am Liu Jiaxiang, a graduate student from Northwestern Polytechnical University. I have recently read your article “SARMV3D-1.0: Synthetic Aperture Radar Microwave Vision 3D Imaging Dataset", there are some questions about the test process of SAR building semantic segmentation dataset. When using Mask RCNN for instance segmentation, what is the category predicted by the classification branch? Because the category information of buildings is not provided in the annotated information, are all buildings regarded as the same category? In addition, if convenient, could you please provide the test source code, so that we can better understand the dataset construction and facilitate subsequent research?