Enhancing Object Detection Performance for Small Objects through Synthetic Data Generation and Proportional Class-Balancing Technique: A Comparative Study in Industrial Scenarios

no code implementations • 23 Jan 2024 • Jibinraj Antony, Vinit Hegiste, Ali Nazeri, Hooman Tavakoli, Snehal Walunj, Christiane Plociennik, Martin Ruskowski

Object Detection (OD) has proven to be a significant computer vision method in extracting localized class information and has multiple applications in the industry.

object-detection Object Detection +1

Federated Object Detection for Quality Inspection in Shared Production

no code implementations • 30 Jun 2023 • Vinit Hegiste, Tatjana Legler, Martin Ruskowski

Federated learning (FL) has emerged as a promising approach for training machine learning models on decentralized data without compromising data privacy.

Federated Learning Object +2

Federated Ensemble YOLOv5 -- A Better Generalized Object Detection Algorithm

no code implementations • 30 Jun 2023 • Vinit Hegiste, Tatjana Legler, Martin Ruskowski

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.

Avg Ensemble Learning +5

Application of federated learning in manufacturing

no code implementations • 9 Aug 2022 • Vinit Hegiste, Tatjana Legler, Martin Ruskowski

A vast amount of data is created every minute, both in the private sector and industry.

Federated Learning