Federated Ensemble YOLOv5 -- A Better Generalized Object Detection Algorithm

TL;DR

This paper explores federated learning applied to object detection with YOLOv5, demonstrating its potential to improve model generalization and accuracy on unseen objects compared to centralized training.

Contribution

It presents a novel perspective of federated learning as an ensemble method, combining Bagging and Boosting, for enhanced object detection performance.

Findings

FL-trained YOLOv5 outperforms centralized models on unseen objects

Global FL model achieves higher accuracy in detecting diverse objects

FL enhances model generalizability and performance

Abstract

Federated learning (FL) has gained significant traction as a privacy-preserving algorithm, but the underlying resemblances of federated learning algorithms like Federated averaging (FedAvg) or Federated SGD (Fed SGD) to ensemble learning algorithms have not been fully explored. The purpose of this paper is to examine the application of FL to object detection as a method to enhance generalizability, and to compare its performance against a centralized training approach for an object detection algorithm. Specifically, we investigate the performance of a YOLOv5 model trained using FL across multiple clients and employ a random sampling strategy without replacement, so each client holds a portion of the same dataset used for centralized training. Our experimental results showcase the superior efficiency of the FL object detector's global model in generating accurate bounding boxes for unseen objects, with the test set being a mixture of objects from two distinct clients not represented in the training dataset. 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.