Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation

TL;DR

This paper introduces a hybrid quantum-classical GAN that generates high-resolution images efficiently, outperforming previous quantum models and matching classical results with significantly fewer parameters.

Contribution

It presents a novel hybrid quantum-classical GAN framework capable of generating high-resolution images without classical pre/post-processing, demonstrating improved efficiency and scalability.

Findings

Generates 28x28 grayscale images without dimensionality reduction.

Achieves results comparable to classical GANs with 1000x fewer parameters.

Increasing quantum generator size enhances learning capability.

Abstract

Quantum machine learning (QML) has received increasing attention due to its potential to outperform classical machine learning methods in problems pertaining classification and identification tasks. A subclass of QML methods is quantum generative adversarial networks (QGANs) which have been studied as a quantum counterpart of classical GANs widely used in image manipulation and generation tasks. The existing work on QGANs is still limited to small-scale proof-of-concept examples based on images with significant downscaling. Here we integrate classical and quantum techniques to propose a new hybrid quantum-classical GAN framework. We demonstrate its superior learning capabilities by generating $28 \times 28$ pixels grey-scale images without dimensionality reduction or classical pre/post-processing on multiple classes of the standard MNIST and Fashion MNIST datasets, which achieves comparable results to classical frameworks with three orders of magnitude less trainable generator parameters. To gain further insight into the working of our hybrid approach, we systematically explore the impact of its parameter space by varying the number of qubits, the size of image patches, the number of layers in the generator, the shape of the patches and the choice of prior distribution. Our results show that increasing the quantum generator size generally improves the learning capability of the network. The developed framework provides a foundation for future design of QGANs with optimal parameter set tailored for complex image generation tasks.