Deep Bilateral Filtering Network (DBFNet)

Code for TIP 2022 paper, "Deep Bilateral Filtering Network for Point-Supervised Semantic Segmentation in Remote Sensing Images", accepted.

Authors: Linshan Wu, Leyuan Fang, Jun Yue, Bob Zhang, Pedram Ghamisi, and Min He

Getting Started

Prepare Dataset

Download the Potsdam and Vaihingen datasets after processing.

Or you can download the datasets from the official website. Then, crop the original images and create point labels following our code in Dataprocess.

If your want to run our code on your own datasets, the pre-process code is also available in Dataprocess.

Evaluate

1. Download the original datasets

2. Download our weights

3. Run our code

python predict.py

Train

1. Train DBFNet

python run/point/p_train.py

2. Generate pseudo labels

python run/point/p_predict_train.py

3. Recursive learning

python run/second/sec_train.py

Citation ✏️ 📄

If you find this repo useful for your research, please consider citing the paper as follows:

@ARTICLE{Wu_DBFNet,
  author={Wu, Linshan and Fang, Leyuan and Yue, Jun and Zhang, Bob and Ghamisi, Pedram and He, Min},
  journal={IEEE Transactions on Image Processing}, 
  title={Deep Bilateral Filtering Network for Point-Supervised Semantic Segmentation in Remote Sensing Images}, 
  year={2022},
  volume={31},
  number={},
  pages={7419-7434},
  doi={10.1109/TIP.2022.3222904}}

For any question, please contact Linshan Wu.