Meta-CD

Pytorch codes of Combining SAM with Limited Data for Change Detection in Remote Sensing [paper]

How to Use (Following SAM-CD)

1. Installation

   • Install FastSAM following the instructions.
   • Modify the Ultralytics source files following the instructions at: 'SAM-CD/models/FastSAM/README.md'.

2. Dataset preparation.

   • Please split the data into training, validation and test sets and organize them as follows:

      YOUR_DATA_DIR
      ├── ...
      ├── train
      │   ├── A
      │   ├── B
      │   ├── label
      ├── val
      │   ├── A
      │   ├── B
      │   ├── label
      ├── test
      │   ├── A
      │   ├── B
      │   ├── label

• Find change line 13 in datasets/Levir_CD.py (or other data-loading .py files), change /YOUR_DATA_ROOT/ to your local dataset directory.

1. Training

   classic CD training: python train_CD.py

   training CD with the proposed task-agnostic semantic learning: python train_SAM_CD.py

   line 16-45 are the major training args, which can be changed to load different datasets, models and adjust the training settings.

2. Inference and evaluation

   inference on test sets: set the chkpt_path and run

   python pred_CD.py

   evaluation of accuracy: set the prediction dir and GT dir, and run

   python eval_CD.py

Dataset Download

In the following, we summarize links to some frequently used CD datasets:

• LEVIR-CD
• WHU-CD (baidu)
• CLCD (Baidu)
• S2Looking
• SYSU-CD

Acknowledgement

Our code is based on SAM-CD.

Cite Meta-CD

If you find this work useful or interesting, please consider citing the following BibTeX entry.

@article{gao2025combining,
  title={Combining SAM With Limited Data for Change Detection in Remote Sensing},
  author={Gao, Junyu and Zhang, Da and Wang, Feiyu and Ning, Lichen and Zhao, Zhiyuan and Li, Xuelong},
  journal={IEEE Transactions on Geoscience and Remote Sensing},
  year={2025},
  publisher={IEEE}
}