https://github.com/xdu-jjgs/SA-MixNet-for-Scribble-based-Road-Extraction

SA-MixNet: Structure-aware Mixup and Invariance Learning for Scribble-supervised Road Extraction in Remote Sensing Images
https://github.com/xdu-jjgs/SA-MixNet-for-Scribble-based-Road-Extraction

Last synced: 2 months ago
JSON representation

SA-MixNet: Structure-aware Mixup and Invariance Learning for Scribble-supervised Road Extraction in Remote Sensing Images

• Host: GitHub
• URL: https://github.com/xdu-jjgs/SA-MixNet-for-Scribble-based-Road-Extraction
• Owner: xdu-jjgs
• License: mit
• Created: 2024-07-07T12:49:46.000Z (7 months ago)
• Default Branch: main
• Last Pushed: 2024-07-15T15:52:47.000Z (7 months ago)
• Last Synced: 2024-08-23T17:22:17.046Z (6 months ago)
• Language: C++
• Size: 9.32 MB
• Stars: 4
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-Mixup - [Code

README

        
# SA-MixNet

1) First, pip install `opencv-python == 4.6.0.66` and replace the `\anaconda3\envs\pytorch\Lib\site-packages\skimage\segmentation\slic_superpixels.py` by the `slic_superpixels.py` in this repository,

to get Road Seed Guided SLIC.

2) Run `road_label_propagation.py` to generate proposal masks.

3) Run `train_mix_D.py` for training and run `test.py` for testing.