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. EAI ArtsIT 2021 – 10th EAI International Conference: ArtsIT, Interactivity & Game Creation, 2-4 Dec 2021, Karlsruhe, Germany (virtual). doi: 10.1007/978-3-030-95531-1_30


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: Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use
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
[thumbnail of Logo_Generation_Using_Regional_Features__A_Faster_R_CNN_Approach_to_Generative_Adversarial_Networks_Final (2).pdf]
Text - Accepted Version
Download (10MB) | Preview


Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email


Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login