量子降噪擴散模型

摘要

近年來，像是 DALL-E、Craiyon 和 Stable Diffusion 等機器學習模型因其能夠從簡潔描述中生成高解析度圖像而受到廣泛關注。與此同時，量子計算展現出令人振奮的進展，特別是在量子機器學習方面，利用量子力學來滿足傳統機器學習算法日益增長的計算需求。本文探討了將量子機器學習和變分量子電路整合，以增強基於擴散的圖像生成模型的效能。具體而言，我們解決了傳統擴散模型的兩個挑戰：低取樣速度和龐大的參數需求。我們引入了兩個量子擴散模型，並使用 MNIST 數字、時尚 MNIST 和 CIFAR-10 來對其能力進行基準測試，與其傳統對應模型進行比較。我們的模型在性能指標 FID、SSIM 和 PSNR 方面超越了具有相似參數數量的傳統模型。此外，我們引入了一個一致性模型單一取樣架構，將擴散過程結合為一個步驟，實現快速的一步圖像生成。

English

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.

量子降噪擴散模型

Quantum Denoising Diffusion Models

摘要

Support