Repository files navigation

This repository is the official PyTorch implementation for FHD:
Feature Hierarchical Differentiation for Remote Sensing Image Change Detection

Figure 1: Comparison of different CD methods. (a) Previous methods. Thedeep features of each temporal RS image are extracted by backbone networks,followed by feature differentiation learning, such as subtraction, concatenation,fusion, and attention. (b). Proposed FHD. We propose a novel FeatureHierarchical Differentiation method with TSF and HD modules to select andfuse critical features. Compared to the previous techniques, the proposed FHDexhibits higher change detection performance.

Figure 2: The framework of our proposed FHD.

To simplify the reproduction steps, we only need to install

pip install torch==1.7.1 torchvision==0.8.2pip install mmcv-full==1.3.8 -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.7.0/index.htmlpip install opencv-python

1. Download fromLEVIR,DSIFN,LEVIR+, andS2Looking.
2. Crop RS images size of 256 × 256, DSIFN did not crop with 512 × 512.
3. Format as follows:

|CD_Dataset|----train|---------|A|---------|B|---------|label|----val...|----test...

DownloadMiT-b2 weights pretrained on ImageNet-1K, and put them in a foldermodel_ckpt/.

# single GPU (V100 16G)bash train_eval.sh

DownloadLEVIR, DSIFN, LEVIR+, S2Looking, and put it in a foldermodel_ckpt/.

# single gpu (V100 16G)bash infer_levir.shbash infer_dsifn.shbash infer_levir+.shbash infer_s2looking.sh

If you find this useful in your research, please consider citing:

@article{pei2022feature,  title={Feature Hierarchical Differentiation for Remote Sensing Image Change Detection},  author={Pei, Gensheng and Zhang, Lulu},  journal={IEEE Geoscience and Remote Sensing Letters},  year={2022},  publisher={IEEE}}