GEGAN: Generative Adversarial Networks Training Based on Gradient Directed Evolutionary Strategy

Deep generative models play a crucial role across various domains, with Generative Adversarial Networks (GANs) leading the advancements in deep generative techniques. However, GANs face challenges like unstable training and mode collapse, impacting image generation quality. In this paper, we introduce an optimization algorithm for GAN training, GEGAN, which leverages a gradient-directed evolutionary strategy. GEGAN integrates gradient and evolutionary algorithms and employs knowledge distillation to guide individual mutation, promoting mutual learning among individuals. Additionally, an accept-reject strategy is utilized in selection to prevent ineffective updates. Experimental results across multiple datasets demonstrate that GEGAN outperforms baseline models by capturing sample distribution features more efficiently, generating diverse samples, and mitigating mode collapse, showcasing its effectiveness from an evolutionary perspective.