Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.07049 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911758142144512 |
|---|---|
| author | Kölle, Michael Stenzel, Gerhard Stein, Jonas Zielinski, Sebastian Ommer, Björn Linnhoff-Popien, Claudia |
| author_facet | Kölle, Michael Stenzel, Gerhard Stein, Jonas Zielinski, Sebastian Ommer, Björn Linnhoff-Popien, Claudia |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07049 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Quantum Denoising Diffusion Models Kölle, Michael Stenzel, Gerhard Stein, Jonas Zielinski, Sebastian Ommer, Björn Linnhoff-Popien, Claudia Quantum Physics Computer Vision and Pattern Recognition 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. |
| title | Quantum Denoising Diffusion Models |
| topic | Quantum Physics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.07049 |