Federated learning based multi-domain image-to-image translation

Yingjun Ge; Xiaodong Wang; Jiting Zhou

doi:10.1117/12.2652535

10 November 2022 Federated learning based multi-domain image-to-image translation

Yingjun Ge, Xiaodong Wang, Jiting Zhou

Proceedings Volume 12331, International Conference on Mechanisms and Robotics (ICMAR 2022); 123315P (2022) https://doi.org/10.1117/12.2652535
Event: International Conference on Mechanisms and Robotics (ICMAR 2022), 2022, Zhuhai, China

Abstract

Multi-domain image-to-image translation is widely used in many areas. However, existing methods need to collect data from different organizations which may violate privacy. Moreover, data silos and data protection regulation make it more difficult to centralize data. To solve this problem, this paper proposes federated learning based multi-domain image-toimage translation, which takes advantage of available data owned by different organizations while protecting data privacy. To improve the quality of translated images, a multi-stage multi-domain translation model is also proposed in this paper. The model uses encoder to extract domain-invariant features and domain specific decoders to generate target domain images. Experiments show that the proposed method achieves better translation results without compromising data privacy.

Citation Download Citation

Yingjun Ge, Xiaodong Wang, and Jiting Zhou "Federated learning based multi-domain image-to-image translation", Proc. SPIE 12331, International Conference on Mechanisms and Robotics (ICMAR 2022), 123315P (10 November 2022); https://doi.org/10.1117/12.2652535

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Computer programming

Data modeling

Network architectures

Data communications

Image quality

Machine learning

Visual process modeling

Keywords/Phrases

Search In:

Publication Years