用连续时间神经网络改进扩散模型，生成更高质量图像且训练更快。
Stable Diffusion with Continuous-time Neural Network
- 采用连续时间细胞神经网络替代离散迭代步骤
- 在MNIST上实现更高质量图像与更快训练速度
- 为高效扩散模型提供新思路，适合图像生成研究者
稳定扩散模型已引领图像生成领域的技术革新，目前处于最先进水平，表现出无与伦比的性能。其核心在于通过迭代卷积或Transformer网络进行去噪的扩散过程。连续时间神经网络天然契合扩散概念，有望实现更高精度与更低能耗的实现。本文探索并验证了细胞神经网络在图像生成中的潜力，结果表明其在常见MNIST数据集上相比离散时间模型具有更优性能，能生成更高品质图像，并实现更快速的训练过程。
原文摘要 · Abstract (English)
Stable diffusion models have ushered in a new era of advancements in image generation, currently reigning as the state-of-the-art approach, exhibiting unparalleled performance. The process of diffusion, accompanied by denoising through iterative convolutional or transformer network steps, stands at the core of their implementation. Neural networks operating in continuous time naturally embrace the concept of diffusion, this way they could enable more accurate and energy efficient implementation. Within the confines of this paper, my focus delves into an exploration and demonstration of the potential of celllular neural networks in image generation. I will demonstrate their superiority in performance, showcasing their adeptness in producing higher quality images and achieving quicker training times in comparison to their discrete-time counterparts on the commonly cited MNIST dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。