Science Score: 67.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 1 DOI reference(s) in README -
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.5%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: CV-ShuchangLyu
- License: apache-2.0
- Language: Python
- Default Branch: main
- Size: 8.27 MB
Statistics
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
PFM-JONet
This paper has already published in TGRS.
This repo is the implementation of "Unsupervised Domain Adaptation for VHR Urban Scene Segmentation via Prompted Foundation Model Based Hybrid Training Joint-Optimized Network". We refer to mmsegmentation and mmagic. Many thanks to SenseTime and their two excellent repos.
 |
Dataset Preparation
We select ISPRS (Postsdam/Vaihingen) and CITY-OSM (Paris/Chicago) as benchmark datasets.
We follow ST-DASegNet for detailed dataset preparation.
 |
PFM-JONet
Install
requirements:
python >= 3.7
pytorch >= 1.11
cuda >= 11.7
This version depends on mmengine and mmcv (2.0.1)
prerequisites: Please refer to MMSegmentation PREREQUISITES.
``` cd PFM-JONet
pip install -e .
chmod 777 ./tools/dist_train.sh
chmod 777 ./tools/dist_test.sh ```
Training
ISPRS UDA-RSSeg task:
``` cd PFM-JONet
./tools/disttrain.sh ./experiments/SAMUDASb5PromptSTAdvbit-b16_upernet.py 2 ```
``` ## We add LoRA training in 2025/04/09 cd PFM-JONet
./tools/disttrain.sh ./experiments/SAMUDASb5PromptSTAdvbit-b16upernetLora.py 2 ```
CITY-OSM UDA_RSSeg task:
``` cd PFM-JONet
./tools/disttrain.sh ./experiments/SAMUDASb5PromptSTAdvbit-b16upernetP2C.py 2 ```
Testing
Trained with the above commands, you can get your trained model to test the performance of your model.
ISPRS UDA-RSSeg task:
``` cd PFM-JONet
./tools/disttest.sh ./experiments/SAMUDASb5PromptSTAdvbit-b16upernet.py ./experiments/SAMUDASb5PromptSTAdvbit-b16upernetresults/iter11000P2V_66.86.pth ```
CITY-OSM UDA_RSSeg task:
``` cd PFM-JONet
CUDAVISIBLEDEVICES=1 python ./tools/test.py ./experiments/SAMUDASb5PromptSTAdvbit-b16upernetP2C.py ./experiments/iter35000P2C56.96.pth --show-dir ./P2C_results ```
If you have any question, please discuss with me by sending email to lyushuchang@buaa.edu.cn.
References
Many thanks to their excellent works * mmsegmentation * mmagic
Please Cite
@ARTICLE{10976421,
author={Lyu, Shuchang and Zhao, Qi and Sun, Yaxuan and Cheng, Guangliang and He, Yiwei and Wang, Guangbiao and Ren, Jinchang and Shi, Zhenwei},
journal={IEEE Transactions on Geoscience and Remote Sensing},
title={Unsupervised Domain Adaptation for VHR Urban Scene Segmentation via Prompted Foundation Model-Based Hybrid Training Joint-Optimized Network},
year={2025},
volume={63},
number={},
pages={1-17},
doi={10.1109/TGRS.2025.3564216}}
Owner
- Name: Shuchang Lyu
- Login: CV-ShuchangLyu
- Kind: user
- Location: Beijing China
- Company: Beihang University
- Repositories: 1
- Profile: https://github.com/CV-ShuchangLyu
PhD student from Beihang University, CV researcher
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - name: "MMSegmentation Contributors" title: "OpenMMLab Semantic Segmentation Toolbox and Benchmark" date-released: 2020-07-10 url: "https://github.com/open-mmlab/mmsegmentation" license: Apache-2.0
GitHub Events
Total
- Watch event: 5
- Push event: 21
Last Year
- Watch event: 5
- Push event: 21