Official implementation for the paper A Novel Multi-Branch Self-Distillation Framework for Optimizing Remote Sensing Change Detection. This code is built upon the OpenCD toolbox and MTKD-CD.
- 31/3/2024 - The code of MBSD-CD has been open-sourced.
The JL1-CD dataset is now publicly available. You can download the checkpoint files from:
The SYSU-CD and CDD datasets can be downloaded through SYSU-CD and CDD (RSAI)
To set up the environment, follow the installation instructions provided in the OpenCD repository.
Below, we use the Changer-MiT-b0 model as an example:
python tools/train.py configs/distill-changer/distill-changer_ex_mit-b0_512x512_200k_cgwx.py --work-dir /path/to/save/models/Changer-mit-b0/initialRun the following command:
python test.py <config-file> <checkpoint>All checkpoint files will soon be open sourced.