基于逐像素任意不确定性估计的扩散模型引导采样
Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation
AI总结：
针对扩散模型缺乏图像质量定量评估的问题，提出在采样阶段利用扰动去噪分数方差估计逐像素任意不确定性，并以此引导采样，在 ImageNet 和 CIFAR-10 上改善低质样本过滤与 FID。
摘要：
尽管生成建模已取得显著进展，但当前扩散模型缺乏一种定量评估图像质量的方法。为解决这一局限，我们提出在扩散模型采样阶段估计逐像素的任意不确定性，并利用该不确定性提升样本生成质量。该不确定性通过专为扩散模型设计的扰动方案，以去噪分数的方差进行计算。随后，我们证明任意不确定性估计与扩散噪声分布的二阶导数相关。我们在 ImageNet 和 CIFAR-10 数据集上评估了不确定性估计算法及不确定性引导采样。在与相关工作的比较中，我们展示了在过滤低质量样本方面的良好结果。此外，我们表明所提出的引导方法在 FID 分数方面带来了更优的样本生成效果。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
