通过像素级不确定性估计提升扩散模型采样质量
Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation
- 在采样阶段估计像素级随机不确定性，基于噪声得分方差
- 在ImageNet和CIFAR-10上显著降低低质样本比例，FID提升
- 适合关注生成质量可控性的图像生成研究者
尽管生成模型取得显著进展，现有扩散模型缺乏量化评估图像质量的方法。为此，我们提出在扩散模型采样过程中估计像素级随机不确定性，并利用该不确定性改进生成样本质量。不确定性通过引入针对扩散模型设计的扰动方案，计算去噪得分的方差得到。我们进一步证明，该不确定性与扩散噪声分布的二阶导数相关。在ImageNet和CIFAR-10数据集上评估了我们的不确定性估计算法及不确定性引导采样方法。相比已有方法，本方法在过滤低质量样本方面表现优异，且在FID评分上实现更优生成效果。
原文摘要 · Abstract (English)
Despite the remarkable progress in generative modelling, current diffusion models lack a quantitative approach to assess image quality. To address this limitation, we propose to estimate the pixel-wise aleatoric uncertainty during the sampling phase of diffusion models and utilise the uncertainty to improve the sample generation quality. The uncertainty is computed as the variance of the denoising scores with a perturbation scheme that is specifically designed for diffusion models. We then show that the aleatoric uncertainty estimates are related to the second-order derivative of the diffusion noise distribution. We evaluate our uncertainty estimation algorithm and the uncertainty-guided sampling on the ImageNet and CIFAR-10 datasets. In our comparisons with the related work, we demonstrate promising results in filtering out low quality samples. Furthermore, we show that our guided approach leads to better sample generation in terms of FID scores.
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。