Skip to content

Repository files navigation

FedRefiner

Official code for the paper "FedRefiner: Robust Federated Learning with Noisy Label Refinement for Remote Sensing".

Installation

pip install -r requirements.txt

Example Usage

python FL_train.py --alg fedrefiner --model resnet18 --dataset RS-5 --noise_rate 0.8 --noise_pattern symmetric

More settings can be found in args.py. Please load the dataset (refer to FedRS to download these datasets) into ./dataset. In ./dataset, there should be two sub folders FedRS and FedRS-5.

Remote Sensing Imagery

Remote Sensing Imagery

Citation

TBD.

Acknowledgments

We sincerely appreciate the authors of the FedRS datasets, and more information can be found in the FedRS.

About

Official codes for JCST paper: FedRefiner: Robust Federated Learning with Noisy Label Refinement for Remote Sensing

Resources

Stars

2 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages