Enhancing Object Detection with Hybrid dataset in Manufacturing Environments: Comparing Federated Learning to Conventional Techniques

TL;DR

This paper compares federated learning and traditional methods for object detection in manufacturing, showing FL's superior robustness and adaptability in diverse, unseen environments using a hybrid dataset.

Contribution

It presents a comprehensive comparison of federated learning with conventional techniques for small object detection in manufacturing environments, emphasizing robustness and environmental adaptability.

Findings

FL outperforms centralized models in diverse conditions

Models maintain high accuracy across different viewpoints and lighting

FL demonstrates resilience in unseen environments

Abstract

Federated Learning (FL) has garnered significant attention in manufacturing for its robust model development and privacy-preserving capabilities. This paper contributes to research focused on the robustness of FL models in object detection, hereby presenting a comparative study with conventional techniques using a hybrid dataset for small object detection. Our findings demonstrate the superior performance of FL over centralized training models and different deep learning techniques when tested on test data recorded in a different environment with a variety of object viewpoints, lighting conditions, cluttered backgrounds, etc. These results highlight the potential of FL in achieving robust global models that perform efficiently even in unseen environments. The study provides valuable insights for deploying resilient object detection models in manufacturing environments.