City Research Online

Logo Generation Using Regional Features: A Faster R-CNN Approach to Generative Adversarial Networks

Ter-Sarkisov, A. ORCID: 0000-0002-1300-6132 & Alonso, E. ORCID: 0000-0002-3306-695X (2022). Logo Generation Using Regional Features: A Faster R-CNN Approach to Generative Adversarial Networks. In: ArtsIT, Interactivity and Game Creation. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. (pp. 442-456). Springer. ISBN 9783030955304 doi: 10.1007/978-3-030-95531-1_30

Abstract

In this paper we introduce Local Logo Generative Adversarial Network (LL-GAN) that uses regional features extracted from Faster R-CNN for logo generation. We demonstrate the strength of this approach by training the framework on a small style-rich dataset of real heavy metal logos to generate new ones. LL-GAN achieves Inception Score of 5.29 and Frechet Inception Distance of 223.94, improving on state-of-the-art models StyleGAN2 and Self-Attention GAN.

Publication Type: Conference or Workshop Item (Paper)
Additional Information: This version of the contribution has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record will be available online at: http://www.springer.com/series/8197?detailsPage=free. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms.
Publisher Keywords: Deep Learning, Generative Adversarial Networks, Logo Generation
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: School of Science & Technology > Computer Science
[img]
Preview
Text - Accepted Version
Download (10MB) | Preview

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login