When Federated Learning Meets Vision: an Outlook on Opportunities and Challenges

Khan, A. R., Zoha, A. , Mohjazi, L. , Sajid, H., Abbasi, Q. and Imran, M. A. (2022) When Federated Learning Meets Vision: an Outlook on Opportunities and Challenges. In: EAI BODYNETS 2021 - 16th EAI International Conference on Body Area Networks: Smart IoT and big data for intelligent health management, Glasgow, Great Britain, 25-26 October 2021, pp. 308-319. ISBN 9783030955939 (doi: 10.1007/978-3-030-95593-9_23)

Abstract

The mass adoption of Internet of Things (IoT) devices, and smartphones has given rise to the era of big data and opened up an opportunity to derive data-driven insights. This data deluge drives the need for privacy-aware data computations. In this paper, we highlight the use of an emerging learning paradigm known as federated learning (FL) for vision-aided applications, since it is a privacy preservation mechanism by design. Furthermore, we outline the opportunities, challenges, and future research direction for the FL enabled vision applications.

• Item Type: Conference Proceedings
• Additional Information: BODYNETS 2021. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 420.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Zoha, Dr Ahmed and Khan, Ahsan Raza and Imran, Professor Muhammad and Abbasi, Professor Qammer and Mohjazi, Dr Lina
• Authors: Khan, A. R., Zoha, A., Mohjazi, L., Sajid, H., Abbasi, Q., and Imran, M. A.
• College/School: College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity; College of Science and Engineering > School of Engineering > Electronics and Nanoscale Engineering
• ISBN: 9783030955939
• Published Online: 11 February 2022
• Copyright Holders: Copyright © 2022 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
• Publisher Policy: Reproduced in accordance with the copyright policy of the publisher