BaMSGAN: Self-Attention Generative Adversarial Network with Blur and Memory for Anime Face Generation

Xu Li (), Bowei Li, Minghao Fang, Rui Huang and Xiaoran Huang
Additional contact information
Xu Li: Department of Computer, Central South University, Changsha 410083, China
Bowei Li: School of Telecommunication Engineering, Xidian University, Xi’an 710126, China
Minghao Fang: Zhejiang University-University of Illinois at Urbana-Champaign Institute, Zhejiang University, Haining 314400, China
Rui Huang: School of Earth Sciences, Zhejiang University, Hangzhou 310000, China
Xiaoran Huang: School of Software Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210023, China

Mathematics, 2023, vol. 11, issue 20, 1-13

Abstract: In this paper, we propose a novel network, self-attention generative adversarial network with blur and memory (BaMSGAN), for generating anime faces with improved clarity and faster convergence while retaining the capacity for continuous learning. Traditional self-attention generative adversarial networks (SAGANs) produce anime faces of higher quality compared to deep convolutional generative adversarial networks (DCGANs); however, some edges remain blurry and distorted, and the generation speed is sluggish. Additionally, common issues hinder the model’s ability to learn continuously. To address these challenges, we introduce a blurring preprocessing step on a portion of the training dataset, which is then fed to the discriminator as fake data to encourage the model to avoid blurry edges. Furthermore, we incorporate regulation into the optimizer to mitigate mode collapse. Additionally, memory data stored in the memory repository is presented to the model every epoch to alleviate catastrophic forgetting, thereby enhancing performance throughout the training process. Experimental results demonstrate that BaMSGAN outperforms prior work in anime face generation, significantly reducing distortion rates and accelerating shape convergence.

Keywords: anime face generation; self-attention generative adversarial network; blur dataset; memory replay; generative adversarial network; self-attention (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/20/4401/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/20/4401/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:20:p:4401-:d:1265576

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().