Prototype-Based Pseudo-Label Denoising for Source-Free Domain Adaptation in Remote Sensing Semantic Segmentation

Network Overview.

• [2026/1/17] 🎉🎉 Our paper is accepted to ICASSP'26.
• [2025/9/21] 😀😀 The [arxiv] paper is available.
• [2025/9/21] ✨✨ The README.md has been updated.
• [2025/9/21] 🤓🤓 The [arxiv] paper has been submitted.
• [2025/9/16] ✨✨ The [arxiv] paper is coming soon.
• [2025/9/15] 🔥🔥 This work was submitted.

TODO

• ☑️ submit to arxiv
• ❎ upload training code
• ❎ upload ProSFDA model weights

1. Creating Virtual Environment

---

Install script

pip install torch==1.10.2+cu111 -f https://mirror.sjtu.edu.cn/pytorch-wheels/cu111/?mirror_intel_list
pip install torchvision==0.11.3+cu111 -f https://download.pytorch.org/whl/torch_stable.html 
pip install mmcv-full==1.5.0 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.10.0/index.html
pip install kornia matplotlib prettytable timm yapf==0.40.1

for CN user:

pip install torch==1.10.2+cu111 -f https://mirror.sjtu.edu.cn/pytorch-wheels/cu111/?mirror_intel_list
pip install torchvision==0.11.3+cu111 -f https://download.pytorch.org/whl/torch_stable.html 
pip install mmcv-full==1.5.0 -f https://download.openmmlab.com/mmcv/dist/cu111/torch1.10.0/index.html
pip install kornia matplotlib prettytable timm yapf==0.40.1

Installation of the reference document refer:

Torch and torchvision versions relationship.

Version relationship of mmcv and torch.

2.Preparation of data sets

---

We selected Postsdam, Vaihingen and LoveDA as benchmark datasets and created train, val, test lists for researchers.

2.1 Download of datasets

ISPRS Potsdam

Potsdam download

The Potsdam dataset is for urban semantic segmentation used in the 2D Semantic Labeling Contest - Potsdam.

The dataset can be requested at the challenge homepage. The '2_Ortho_RGB.zip', '3_Ortho_IRRG.zip' and '5_Labels_all_noBoundary.zip' are required.

ISPRS Vaihingen

Vaihingen download

The Vaihingen dataset is for urban semantic segmentation used in the 2D Semantic Labeling Contest - Vaihingen.

The dataset can be requested at the challenge homepage. The 'ISPRS_semantic_labeling_Vaihingen.zip' and 'ISPRS_semantic_labeling_Vaihingen_ground_truth_eroded_COMPLETE.zip' are required.

2.2 Data set preprocessing

Place the downloaded file in the corresponding path The format is as follows:

detals

ProSFDA/
├── data/
├── ├── Potsdam_IRRG_DA/
│   │   ├── 3_Ortho_IRRG.zip
│   │   └── 5_Labels_all_noBoundary.zip
├── ├── Vaihingen_IRRG_DA/
│   │   ├── ISPRS_semantic_labeling_Vaihingen.zip
│   │   └── ISPRS_semantic_labeling_Vaihingen_ground_truth_eroded_COMPLETE.zip

after that we can convert dataset:

dataset convert

• Potsdam

python tools/convert_datasets/potsdam.py data/Potsdam_IRRG/ --clip_size 512 --stride_size 512
python tools/convert_datasets/potsdam.py data/Potsdam_RGB/ --clip_size 512 --stride_size 512

• Vaihingen

python tools/convert_datasets/vaihingen.py data/Vaihingen_IRRG/ --clip_size 512 --stride_size 256

3.Training

---

3.1 Preparation of pre-trained models

mit_b5.pth : We provide a script mit2mmseg.py in the tools directory to convert the key of models from the official repo to MMSegmentation style.

model convert

python tools/model_converters/mit2mmseg.py ${PRETRAIN_PATH} ./pretrained

Or you can download it from google drive.

The structure of the file is as follows

structure

ProSFDA/
├── pretrained/
│   ├── mit_b5.pth (needed)
│   └── ohter.pth  (optional)

---

The training code will be updated shortly. Please be patient 🤗🤗.