F3Net: Feature Filtering Fusing Network for Change Detection of Remote Sensing Images

The paper has been accepted by JSTARS

f3net torch code.

weights, and program are created using paddle.

F3Net program: AI Studio

F3Net weights can be found at Baidu or GoogleCloud, and the complete code will be released after the paper is accepted.

Please cite our paper if you use this code in your work link:

@ARTICLE{10540196,
  author={Huang, Junqing and Yuan, Xiaochen and Lam, Chan-Tong and Huang, Guoheng},
  journal={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, 
  title={F3Net: Feature Filtering Fusing Network for Change Detection of Remote Sensing Images}, 
  year={2024},
  volume={17},
  number={},
  pages={10621-10635},
  keywords={Feature extraction;Remote sensing;Noise;Deep learning;Task analysis;Filtering;Transformers;Change detection;deep learning;multiple receptive fields;noise information},
  doi={10.1109/JSTARS.2024.3405971}}