International Conference on Big Data Analytics in Bioinformatics (DABCon)

Image Generation with Quantum Generative Adversarial Networks Using Numeric and Fashion Mnist Images

Deepanshi Joon, Rishu Raj, Garvit Nama, Meena Pundir

Published Nov 21, 2024• 2 citations

Abstract

This study explores the frontiers of generative modelling by introducing quantum principles into the picture synthesis process via Quantum Generative Adversarial Networks (QGANs). QGANs provide a novel method to image production by utilising the intrinsic features of quantum systems to improve both the quantity and variety of generated images. Using the Fashion-MNIST dataset and Numeric dataset, which consists of 28×28 grayscale images depicting various fashion products, this study investigates the potential of QGANs in creating realistic and diversified fashion images across multiple classes. While this study, Obtained 0.50 Discriminator Loss along with 0.98 as Generator Loss on 90thEpoch for numeric dataset. This research demonstrates that QGANs can surpass classical models in terms of image generation, as evidenced by improved metrics and computational advantages. Additionally, by integrating physics principles such as the conservation of quantum information, this QGAN framework paves the way for disruptive advancements in computer vision, fashion design, and digital media production.

DOI: 10.1109/dabcon63472.2024.10919418

Related papers

High-Resolution Fashion Image Generation using Quantum-GAN

Ashish Solanki, Sandeep Singh Kang, Sanjay Singla +1 more

Generative Adversarial Networks (GANs) is had proven the great results for image generation which opens the gateway for quantum researcher's. But the implementation on quantum computers is not straightforward as each pixel resembles single qubits and to process the 28x28 image it requires 784 qubits. Based on current resources at the number of qubits increase computational time increases. This study explores QGAN potentials to provide a method for generating images using features of quantum systems to improve the quantity and quality of the generated images. This research use the Fashion MNIST dataset because it this dataset has simple as well as complex structures and it consists of 28x28 gray-scale images with 9 fashion products. By considering those limitation of quantum resources for classical computers. Quantum-GAN framework use Principal Component Analysis (PCA) to reduce the number of features. In addition to that, framework is using shallow-depth quantum circuit and a reduced parameter set. This research also deals with vanishing gradient problem of GANs and to overcome this problem of this framework uses Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for fine-tuning training parameters of quantum circuits.

International Conference on Technological Innovations and Advance Computing (TIACOMP)Jun 29, 20243 citations

Quantum generative adversarial network for image generation

Mohammadsaleh Pajuhanfard, Ziwen Pan, Victor S. Sheng

Abstract Quantum machine learning as a field has emerged rather quickly thanks to developments in quantum computing. Of these developments, the one of primary interest is the Quantum Generative Adversarial Network or QGAN which is an enhancement of the familiar GAN to use quantum computation necessary for producing synthetic images. To sum up, based on different types of experiments, QGANs outperformed classical GANs, especially in cases with images such as MNIST and Fashion MNIST datasets. Nevertheless, their capabilities are not fully comprehensible due to existing constraints in quantum systems technology, especially in the NISQ era. In this regard, the current study undertakes a proposed research direction that focuses on improving the resolution of grayscale images that have been produced from the “optdigits” dataset, which contains handwritten digit images. Our work then contrasts this with prior work in terms of FID scores, loss function values, runtime, and the resolution of the images. Further, we extend the work by carrying out the proposed methodology on the FMNIST dataset and provide results to corroborate the efficacy of the proposed technique, besides enabling comparison on the same platform with prior works.

The Visual ComputerMay 13, 202513 citations

Quantum Generative Neural Networks for Imaging Applications

Sunil Vittal, David Ramirez, Glen S. Uehara +2 more

Quantum Machine Learning has received a lot of attention recently in the research community due to its potential to provide computational advantages in areas including training neural networks and big data analytics. In this paper, we focus on generative approaches using quantum machine learning. Specifically, we train QuantumClassical Hybrid Generative Adversarial Networks (qGANs) for imaging applications. We use the MNIST and Fashion-MNIST datasets in our qGAN simulations, and we present examples that generate small-scale grayscale images of the zero digit and shirts classes. In our research, we used Xanadu's PennyLane quantum programming software to implement and evaluate our algorithms. Challenges in our study included long computational times and large memory requirements for training the qGAN. However, our results revealed that our proposed hybrid model achieves a higher average PSNR, a lower FID score, but a lower Inception score than a classical GAN.

International Conference on Information, Intelligence, Systems & Applications (IISA)Jul 10, 20252 citations

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

Shu Lok Tsang, Maxwell T. West, Sarah Erfani +1 more

Quantum machine learning (QML) has received increasing attention due to its potential to outperform classical machine learning methods in problems such as 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 down-scaling. Here we integrate classical and quantum techniques to propose a new hybrid quantum-classical GAN framework. We demonstrate its superior learning capabilities over existing quantum techniques by generating 28×28 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

arXiv:2212.11614IEEE Transactions on Quantum EngineeringJan 1, 2023111 citations

Latent Style-based Quantum GAN for high-quality Image Generation

Su Yeon Chang, Supanut Thanasilp, Bertrand Le Saux +2 more

Quantum generative modeling is among the promising candidates for achieving a practical advantage in data analysis. Nevertheless, one key challenge is to generate large-size images comparable to those generated by their classical counterparts. In this work, we take an initial step in this direction and introduce the Latent Style-based Quantum GAN (LaSt-QGAN), which employs a hybrid classical-quantum approach in training Generative Adversarial Networks (GANs) for arbitrary complex data generation. This novel approach relies on powerful classical auto-encoders to map a high-dimensional original image dataset into a latent representation. The hybrid classical-quantum GAN operates in this latent space to generate an arbitrary number of fake features, which are then passed back to the auto-encoder to reconstruct the original data. Our LaSt-QGAN can be successfully trained on realistic computer vision datasets beyond the standard MNIST, namely Fashion MNIST (fashion products) and SAT4 (Earth Observation images) with 10 qubits, resulting in a comparable performance (and even better in some metrics) with the classical GANs. Moreover, we analyze the barren plateau phenomena within this context of the continuous quantum generative model using a polynomial depth circuit and propose a method to mitigate the detrimental effect during the training of deep-depth networks. Through empirical experiments and theoretical analysis, we demonstrate the potential of LaSt-QGAN for the practical usage in the context of image generation and open the possibility of applying it to a larger dataset in the future.

arXiv:2406.02668Jun 4, 20247 citations

Quantum Generative Adversarial Networks for Synthetic Data Augmentation

Jincheng Zhang

This paper explores the application of Quantum Generative Adversarial Networks (QGANs) for synthetic data augmentation, aiming to surpass the limitations of classical Generative Adversarial Networks (GANs). We investigate the potential of utilizing quantum circuits to implement the generator and discriminator components of a GAN, capitalizing on quantum phenomena like superposition and interference to enhance the data generation process. Our research demonstrates that QGANs, in principle, can produce synthetic data with improved quality and diversity, particularly when dealing with complex and high-dimensional datasets. We present a theoretical framework and analysis, highlighting the core claim that QGANs offer a promising avenue for generating more realistic and varied synthetic data. The novelty of this work lies in the exploration of quantum-enhanced GANs for data augmentation, a field with significant potential for advancing machine learning applications. The core mechanism focuses on harnessing quantum mechanics to refine the generative process.

Sep 5, 20260 citations