2026-10-14T12:44:38Z https://www.scidb.cn/oai

10.57760/sciencedb.44566 2026-07-28T08:49:45Z

2026-07-28 Source Code for FedRefiner: Robust Federated Learning with Noisy Label Refinement for Remote Sensing doi:10.57760/sciencedb.44566 en This dataset provides the official source code for the paper FedRefiner: Robust Federated Learning with Noisy Label Refinement for Remote Sensing. It supports reproduction of FedRefiner, a federated learning method for remote sensing imagery with noisy labels. The code implements a two-stage training procedure. The first stage performs robust warm-up with symmetric cross entropy. The second stage uses a dual-view two-component Gaussian mixture model to separate reliable and noisy samples, then combines high-confidence label correction with a learning-to-cluster objective for representation optimization. All sample selection, label correction, and representation optimization are performed locally on each client, and only model parameters are uploaded. The package includes the training entry point, algorithm implementations, model and data utilities, dependency specifications, and usage instructions. The FedRS-5 and FedRS-15 datasets should be obtained separately through the links in the README. FedRefiner; federated learning; remote sensing; data quality wu lü hua PUBLIC https://api.github.com/licenses/apache-2.0 dataset Science Data Bank