Quantum Denoising Diffusion Models
This addresses computational bottlenecks in diffusion-based image generation for AI researchers, though it appears incremental as it builds on existing quantum and diffusion methods.
The paper tackles the low sampling speed and high parameter requirements of classical diffusion models by introducing quantum diffusion models that outperform classical counterparts on MNIST, Fashion MNIST, and CIFAR-10 datasets in metrics like FID, SSIM, and PSNR, and also proposes a consistency model for fast one-step image generation.
In recent years, machine learning models like DALL-E, Craiyon, and Stable Diffusion have gained significant attention for their ability to generate high-resolution images from concise descriptions. Concurrently, quantum computing is showing promising advances, especially with quantum machine learning which capitalizes on quantum mechanics to meet the increasing computational requirements of traditional machine learning algorithms. This paper explores the integration of quantum machine learning and variational quantum circuits to augment the efficacy of diffusion-based image generation models. Specifically, we address two challenges of classical diffusion models: their low sampling speed and the extensive parameter requirements. We introduce two quantum diffusion models and benchmark their capabilities against their classical counterparts using MNIST digits, Fashion MNIST, and CIFAR-10. Our models surpass the classical models with similar parameter counts in terms of performance metrics FID, SSIM, and PSNR. Moreover, we introduce a consistency model unitary single sampling architecture that combines the diffusion procedure into a single step, enabling a fast one-step image generation.