Adaptive federated learning for ship detection across diverse satellite imagery sources
This provides a privacy-preserving solution for ship detection using commercial or sensitive satellite imagery, though it's incremental in applying existing FL methods to this domain.
The paper tackles ship detection across diverse satellite imagery sources using federated learning to preserve privacy while avoiding data sharing. Results show FL models substantially improve detection accuracy over local training and approach performance of global training with all data.
We investigate the application of Federated Learning (FL) for ship detection across diverse satellite datasets, offering a privacy-preserving solution that eliminates the need for data sharing or centralized collection. This approach is particularly advantageous for handling commercial satellite imagery or sensitive ship annotations. Four FL models including FedAvg, FedProx, FedOpt, and FedMedian, are evaluated and compared to a local training baseline, where the YOLOv8 ship detection model is independently trained on each dataset without sharing learned parameters. The results reveal that FL models substantially improve detection accuracy over training on smaller local datasets and achieve performance levels close to global training that uses all datasets during the training. Furthermore, the study underscores the importance of selecting appropriate FL configurations, such as the number of communication rounds and local training epochs, to optimize detection precision while maintaining computational efficiency.