Adaptive federated learning for ship detection across diverse satellite imagery sources

TL;DR

This paper explores federated learning for ship detection in satellite images, demonstrating improved accuracy and privacy preservation without sharing raw data, and analyzing optimal FL configurations for performance and efficiency.

Contribution

It introduces federated learning models for satellite ship detection, comparing their performance to local and global training, and highlights optimal FL setup strategies.

Findings

FL models outperform local training in accuracy

FL models approach global training performance

Proper FL configuration enhances efficiency and precision

Abstract

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.