REVIEW 6 cited by
Latent Style-based Quantum GAN for high-quality Image Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 6 Pith papers
-
Scaling Quantum Machine Learning without Tricks: Full-Resolution and Diverse Image Generation
A single end-to-end quantum generator using an image-tailored circuit and learnable multimodal noise achieves state-of-the-art simulated FID scores on full MNIST and Fashion-MNIST without tricks.
-
Pitfalls when tackling the exponential concentration of parameterized quantum models
Exponentially concentrated measurement outcomes are statistically indistinguishable from fixed noise after polynomial shots, so classical post-processing cannot fix them, and common proposed remedies do not escape this.
-
Improving GANs by leveraging the quantum noise from real hardware
Using bitstrings from a 16-qubit entangling circuit as a Gaussian latent prior lowers FID in WGAN, SNGAN, and BigGAN on CIFAR-10 versus a standard Gaussian.
-
Inverse Design using Physics-Informed Quantum GANs for Tailored Absorption in Dielectric Metasurfaces
A hybrid quantum GAN with a Fano-based physics loss is proposed for inverse design of narrow-band absorbing metasurfaces, claiming data-efficient generation of high-Q designs.
-
Hybrid Quantum-Classical Inverse Design of Metasurfaces for Tailored Narrow Band Absorption
A hybrid quantum-classical GAN (LaSt-QGAN) is applied to metasurface inverse design, claiming 10x faster training, 40x less data, and generation of Q-factors up to 10^4 from a training set with Q-factors up to 10^3.
-
Hybrid Quantum Generative Adversarial Networks To Inverse Design Metasurfaces For Incident Angle-Independent Unidirectional Transmission
A hybrid quantum GAN with a variational autoencoder is applied to inverse-design dielectric metasurfaces for directional far-field patterns and then to boost simulated perovskite solar-cell efficiency.
Discussion (0). Sign in to comment.