Dual-Discriminator Hybrid Quantum Generative Adversarial Networks for Improved GAN Performance

This study presents an investigation of the dual-discriminator hybrid quantum generative adversarial network (DDHQ-GAN), a framework designed to enhance the performance of conventional generative adversarial networks (GANs) through the incorporation of a hybrid quantum discriminator. The proposed DDHQ-GAN architecture comprises three primary components: a generator and two discriminators. The research evaluates the efficacy of the DDHQ-GAN in comparison with existing GAN variants, employing the Fréchet inception distance (FID) as a quantitative metric to assess image generation quality. The study further examines the interplay between the structural configurations of parameterized quantum circuits, classical neural network architectures, and model hyperparameters, using the Modified National Institute of Standards and Technology (MNIST) dataset as the experimental benchmark. Empirical results demonstrate that the DDHQ-GAN achieves superior performance, reflected by lower FID scores, while incurring only a marginal increase in the number of parameters and quantum computational resources.