---
license: mit
library_name: pytorch
pipeline_tag: image-to-image
---

# JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework

This repository contains the model presented in the paper [JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework](https://arxiv.org/pdf/2502.13407).  This model utilizes a multi-teacher knowledge distillation (MTKD) framework for change detection (CD) in remote sensing images.

## Dataset

The JL1-CD dataset is publicly available and can be downloaded from:

- [Google Drive](https://drive.google.com/drive/folders/1ELoqx7J3GrEFMX5_rRynMjW9-Poxz3Uu?usp=sharing)
- [Baidu Disk](https://pan.baidu.com/s/1_vcO4c5DM5LDuOqLwLrWJg?pwd=5byn)
- [Hugging Face](https://huggingface.co/datasets/circleLZY/JL1-CD)


## Usage

### Install

To set up the environment, follow the installation instructions provided in the [OpenCD repository](https://github.com/likyoo/open-cd).

### Training

The training process for the MTKD framework consists of three steps. Below, we use the **Changer-MiT-b0** model as an example:

#### Step 1: Train the original model


#### Step 2: Train teacher models for different CAR partitions (e.g., 3 partitions)


#### Step 3: Train the student model




### Testing




#### Checkpoints

You can download checkpoint files from:
- [Baidu Disk](https://pan.baidu.com/s/1F5MIGCCiNHFifNl_kDiklA?pwd=4tid)
- [Hugging Face](https://huggingface.co/circleLZY/MTKD)


## Citation

If you find the JL1-CD dataset or our work useful in your research, please consider citing our paper:

```bibtex
@article{liu2025jl1,
  title={JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework},
  author={Liu, Ziyuan and Zhu, Ruifei and Gao, Long and Zhou, Yuanxiu and Ma, Jingyu and Gu, Yuantao},
  journal={arXiv preprint arXiv:2502.13407},
  year={2025}
}
```

Code: https://github.com/circleLZY/MTKD-CD.