This paper explores the application of Federated Learning (FL) to object detection as a method to enhance generalizability and compares its performance against a centralized training approach for an object detection algorithm. The authors investigate the performance of a YOLOv5 model trained using FL across multiple clients and employ a random sampling strategy without replacement. The experimental results showcase the superior efficiency of the FL object detector’s global model in generating accurate bounding boxes for unseen objects. These findings suggest that FL can be viewed from an ensemble algorithm perspective, akin to a synergistic blend of Bagging and Boosting techniques. As a result, FL can be seen not only as a method to enhance privacy, but also as a method to enhance the performance of a machine learning model.

 

Publication date: June 30, 2023
Project Page: N/A
Paper: https://arxiv.org/pdf/2306.17829.pdf