Deakin University
Browse

File(s) under embargo

Fed4ReID: Federated Learning with Data Augmentation for Person Re-identification Service in Edge Computing

conference contribution
posted on 2023-10-26, 04:38 authored by Chong ZhangChong Zhang, Xiao LiuXiao Liu, Mingrong Xiang, A Yao, X Fan, Gang LiGang Li
Federated learning is a new distributed privacy-preserving learning paradigm which perfectly meets the requirements of many large service systems such as banking, healthcare, and smart city. Meanwhile, person re-identification, as a technology to associate the images of the same person from different data sources, has been widely used in many smart services such as smart logistics, smart surveillance, and many public searching and rescue missions. Therefore, it is a promising solution to use federated learning for person re-identification to improve the model accuracy while protecting the data privacy. However, the common problem of non-independent and identically distributed (Non-IID) data with heterogeneous clients in federated learning often causes undesirable model accuracy. To address such a problem, in this paper, we propose a novel strategy named federated learning with data augmentation for person re-identification (Fed4ReID). Specifically, to alleviate the impact of Non-IID data, we utilise a pre-trained DCGAN (Deep Convolutional Generative Adversarial Network) model for data augmentation at each edge servers. Experiments on public datasets show that our proposed strategy can outperform baseline method in general accuracy.

History

Volume

00

Pagination

64-70

Location

Chicago, Illinois

Start date

2023-07-02

End date

2023-07-08

ISBN-13

9798350304855

Language

eng

Publication classification

E1 Full written paper - refereed

Title of proceedings

Proceedings - 2023 IEEE International Conference on Web Services, ICWS 2023

Event

2023 IEEE International Conference on Web Services (ICWS)

Publisher

IEEE

Place of publication

Piscataway, N.J.

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC