Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images. However, critical questions remain unanswered regarding how quantum principles might best enhance their representational and computational capacity. In this paper, we investigate hybrid quantum-classical GAN architectures supplemented by transfer learning to systematically examine whether incorporating Variational Quantum Circuits (VQCs) into the generator, the discriminator, or both improves performance over a fully classical baseline. Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, produce images with higher quality and achieve more favorable quantitative metrics compared to their fully classical counterparts. In particular, placing the quantum block in the generator appears to accelerate the early emergence of visual structure, whereas placing it in the discriminator slows early visual convergence but improves the final quantitative quality metric. Incorporating quantum blocks into both networks yields the strongest overall performance. Moreover, the model sustains comparable performance even when the dataset size is reduced. Overall, the results underscore that carefully integrating quantum computing with classical adversarial training and pretrained feature extraction can enrich GAN-based image synthesis. These insights open avenues for future work on higher-resolution tasks, alternative quantum circuit designs, and experimentation with emerging quantum hardware.
Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images. However, critical questions remain unanswered regarding how quantum principles might best enhance their representational and computational capacity. In this paper, we investigate hybrid quantum-classical GAN architectures supplemented by transfer learning to systematically examine whether incorporating Variational Quantum Circuits (VQCs) into the generator, the discriminator, or both improves performance over a fully classical baseline. Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, produce images with higher quality and achieve more favorable quantitative metrics compared to their fully classical counterparts. In particular, placing the quantum block in the generator appears to accelerate the early emergence of visual structure, whereas placing it in the discriminator slows early visual convergence but improves the final quantitative quality metric. Incorporating quantum blocks into both networks yields the strongest overall performance. Moreover, the model sustains comparable performance even when the dataset size is reduced. Overall, the results underscore that carefully integrating quantum computing with classical adversarial training and pretrained feature extraction can enrich GAN-based image synthesis. These insights open avenues for future work on higher-resolution tasks, alternative quantum circuit designs, and experimentation with emerging quantum hardware.
Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images; however, critical questions remain regarding how quantum principles might best enhance their representational capacity. This thesis investigates hybrid quantum-classical GAN architectures supplemented by transfer learning in the discriminator, systematically examining whether incorporating Variational Quantum Circuits (VQCs) into the generator, the discriminator, or both improves performance over fully classical baselines. We evaluate each configuration using standard GAN benchmarks (CIFAR-10 classes: Birds, Cars, and Dogs) under varying sample sizes (5,000 vs. 2,500 images per class) to gauge both robustness and data efficiency. Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, consistently produce images of higher visual quality and achieve more favorable quantitative metrics (such as Fréchet Inception Distance (FID), Kernel Inception Distance (KID), and Inception Score (IS)) compared to their fully classical counterpart. In particular, VQCs in the generator accelerate early feature learning, whereas those in the discriminator, despite exhibiting slower initial convergence, ultimately facilitate more refined synthetic outputs. Moreover, the model sustains near-comparable performance even when the dataset size is halved, suggesting that transfer learning and quantum enhancements mitigate data limitations. By comparing classical and hybrid configurations in detail, this thesis illustrates the trade-offs arising from VQCs in GANs, such as variations in early-epoch convergence and final generative quality. Overall, the results underscore that carefully integrating quantum computing principles with classical adversarial training and pretrained feature extraction can significantly enrich GAN-based image synthesis. These insights open avenues for future work on higher-resolution tasks, alternative quantum circuit designs, and experimentation with emerging quantum hardware.
Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images; however, critical questions remain regarding how quantum principles might best enhance their representational capacity. This thesis investigates hybrid quantum-classical GAN architectures supplemented by transfer learning in the discriminator, systematically examining whether incorporating Variational Quantum Circuits (VQCs) into the generator, the discriminator, or both improves performance over fully classical baselines. We evaluate each configuration using standard GAN benchmarks (CIFAR-10 classes: Birds, Cars, and Dogs) under varying sample sizes (5,000 vs. 2,500 images per class) to gauge both robustness and data efficiency. Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, consistently produce images of higher visual quality and achieve more favorable quantitative metrics (such as Fréchet Inception Distance (FID), Kernel Inception Distance (KID), and Inception Score (IS)) compared to their fully classical counterpart. In particular, VQCs in the generator accelerate early feature learning, whereas those in the discriminator, despite exhibiting slower initial convergence, ultimately facilitate more refined synthetic outputs. Moreover, the model sustains near-comparable performance even when the dataset size is halved, suggesting that transfer learning and quantum enhancements mitigate data limitations.By comparing classical and hybrid configurations in detail, this thesis illustrates the trade-offs arising from VQCs in GANs, such as variations in early-epoch convergence and final generative quality. Overall, the results underscore that carefully integrating quantum computing principles with classical adversarial training and pretrained feature extraction can significantly enrich GAN-based image synthesis. These insights open avenues for future work on higher-resolution tasks, alternative quantum circuit designs, and experimentation with emerging quantum hardware.
Generative adversarial network (GAN) is one of the widely-adopted machine-learning frameworks for a wide range of applications such as generating high-quality images, video, and audio contents. However, training a GAN could become computationally expensive for large neural networks. In this work, we propose a hybrid quantum-classical architecture for improving GAN (denoted as QC-GAN). The performance was examed numerically by benchmarking with a classical GAN using MindSpore Quantum on the task of hand-written image generation. The generator of the QC-GAN consists of a quantum variational circuit together with a one-layer neural network, and the discriminator consists of a traditional neural network. Leveraging the entangling and expressive power of quantum circuits, our hybrid architecture achieved better performance (Frechet Inception Distance) than the classical GAN, with much fewer training parameters and number of iterations for convergence. We have also demonstrated the superiority of QC-GAN over an alternative quantum GAN, namely pathGAN, which could hardly generate 16$\times$16 or larger images. This work demonstrates the value of combining ideas from quantum computing with machine learning for both areas of Quantum-for-AI and AI-for-Quantum.
Quantum Generative Adversarial Networks (QGANs), as a rising paradigm in Quantum Machine Learning, have shown promising potential in image generation and processing. However, their output quality remains suboptimal, and existing research is largely limited to small-scale, proof-of-concept studies. In this work, we propose a hybrid quantum-classical GAN architecture, where the generator integrates parameterized quantum circuits (PQCs) and classical neural networks. This integration significantly enhances the visual quality of generated images. Our model leverages the complementary strengths of quantum and classical components and outperforms existing methods (Tsang et al. in IEEE Trans. Quantum Eng. 4:1–19, 2023 ; Gulrajani et al. in Proceedings of the 31st international conference on neural information processing systems. NIPS’17, Red Hook, pp. 5769–5779, 2017 ), particularly in terms of image fidelity. Experiments conducted on the MNIST family of datasets show that our hybrid approach achieves a 20.26% average reduction in Fréchet Inception Distance. Furthermore, it improves the Structural Similarity Index Measure, Cosine Similarity, and Peak Signal-to-Noise Ratio by 26.04%, 2.22%, and 7.62%, respectively. These results highlight the effectiveness of combining quantum computing with machine learning, and underscore the potential of hybrid quantum-classical models in advancing generative tasks.
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 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.
Hybrid Quantum Generative Adversarial Networks (HQ-GANs) have emerged as a promising class of models at the intersection of quantum computing and generative artificial intelligence. Unlike early quantum generative approaches that relied on fully quantum pipelines, hybrid QGANs combine parameterized quantum circuits with classical optimization and discrimination mechanisms, enabling practical training under the constraints of noisy intermediate-scale quantum (NISQ) hardware. This paper presents a comprehensive technical review of hybrid QGAN architectures, with a particular focus on implicit quantum representations and hybrid optimization strategies that enhance expressivity, stability, and scalability. We analyze how recent advances in variational circuit design, data re-encoding, Wasserstein-based objectives, and hybriddepth control have reshaped the feasibility of quantum generative learning. New mathematical formulations are introduced to describe implicit quantum mappings and hybrid adversarial convergence. Comparative analysis highlights performance trends, architectural trade-offs, and unresolved challenges related to noise, barren plateaus, and hardware–software mismatch. The paper concludes by outlining future research directions toward robust, application-ready quantum generative intelligence.