EUVIMEDEUVIMED entdecken
Crossref

Evolutionary Channel Pruning for Style-Based Generative Adversarial Networks

Yixia Zhang iD, Ferrante Neri iD, Xilu Wang iD, Pengcheng Jiang iD, Yu Xue iD

International Journal of Neural Systems · 2026

DOI: 10.1142/s0129065725500704 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Neural Systems, 2026. Verfasst von Yixia Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Electronic Engineering, University of Surrey, Guildford, United Kingdom. Hauptthemen laut MEDLINE: Neural Networks, Computer, Algorithms, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Natural Science Foundation of the Jiangsu Higher Education Institutions of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generative Adversarial Networks (GANs) have demonstrated remarkable success in high-quality image synthesis, with StyleGAN and its successor, StyleGAN2, achieving state-of-the-art performance in terms of realism and control over generated features. However, the large number of parameters and high floating-point operations per second (FLOPs) hinder real-time applications and scalability, posing challenges for deploying these models in resource-constrained environments such as edge devices and mobile platforms. To address this issue, we propose Evolutionary Channel Pruning for StyleGANs (ECP-StyleGANs), a novel algorithm that leverages evolutionary algorithms to compress StyleGAN and StyleGAN2 while maintaining competitive image quality. Our approach encodes pruning configurations as binary masks on the model’s convolutional channels and iteratively refines them through selection, crossover, and mutation. By integrating carefully designed fitness functions that balance model complexity and generation quality, ECP-StyleGANs identifies optimally pruned architectures that reduce computational demands without compromising visual fidelity, achieving approximately a 4 × reduction in FLOPs and parameters, while maintaining visual fidelity with only a slight increase in FID (Fréchet Inception Distance) compared to the original un-pruned model. This study should be interpreted as a preliminary step towards the formulation and management of the generative AI pruning problem as a multi-objective optimisation task, aimed at enhancing the trade-off between model efficiency and image quality, thereby making large deep models more accessible for real-world applications such as edge devices and resource-constrained environments. Source codes will be available.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerAlgorithmsImage Processing, Computer-AssistedHumansGenerative Adversarial Networks

Stichwörter der Autor:innen

StyleGANschannel pruningevolutionary algorithmgenerative AI

Autor:innen und Institutionen

  • School of Computer Science and Electronic Engineering, University of Surrey, Guildford, United Kingdom.
  • School of Software, Nanjing University of Information Science and Technology, Nanjing, P. R. China.

ORCID-Profile: Yixia Zhang, Ferrante Neri, Xilu Wang, Pengcheng Jiang, Yu Xue

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangsu Province
  • Natural Science Foundation of the Jiangsu Higher Education Institutions of China

Zitieren

APA

Zhang, Y., Neri, F., Wang, X., Jiang, P., & Xue, Y. (2026). Evolutionary Channel Pruning for Style-Based Generative Adversarial Networks. International Journal of Neural Systems. https://doi.org/10.1142/s0129065725500704

Vancouver

Zhang Y, Neri F, Wang X, Jiang P, Xue Y. Evolutionary Channel Pruning for Style-Based Generative Adversarial Networks. International Journal of Neural Systems. 2026. doi:10.1142/s0129065725500704

BibTeX
@article{Zhang2026,
  author = {Zhang, Yixia and Neri, Ferrante and Wang, Xilu and Jiang, Pengcheng and Xue, Yu},
  title = {Evolutionary Channel Pruning for Style-Based Generative Adversarial Networks},
  journal = {International Journal of Neural Systems},
  year = {2026},
  doi = {10.1142/s0129065725500704}
}
Kostenlos starten →