ICSO: A Novel Hybrid Evolutionary Approach with Crisscross and Perturbation Mechanisms for Optimizing Generative Adversarial Network Latent Space

Hybrid evolutionary approaches have gained significant attention for solving complex optimization problems, but their potential for optimizing the low-dimensional latent space of generative adversarial networks (GANs) remains underexplored. This paper proposes a novel improved crisscross optimizatio...

Full description

Bibliographic Details

Published in:	Applied Sciences
Main Authors:	Zhihui Chen, Ting Lan, Zhanchuan Cai, Zonglin Liu, Renzhang Chen
Format:	Article
Language:	English
Published:	MDPI AG 2025-05-01
Subjects:	crisscross optimization evolutionary optimization generative adversarial network latent space particle swarm optimization
Online Access:	https://www.mdpi.com/2076-3417/15/10/5228