论文标题
源分离与深度生成先验
Source Separation with Deep Generative Priors
论文作者
论文摘要
尽管信号源分离方面取得了长足的进展，但结构化数据的结果仍然包含可感知的伪影。相比之下，最近的深层生成模型可以在各种域中产生真实的样品，这些样本与数据分布的样本无法区分。本文介绍了一种贝叶斯分离方法，该方法将生成模型用作源混合物组成部分的先验，并从噪声响起的Langevin动力学中从源后验分布中进行采样。这将源分离问题与生成建模相解开，使我们能够直接将尖端生成模型作为先验。该方法实现了MNIST数字分离的最新性能。我们引入了新的方法，用于评估富裕数据集的分离质量，从而对CIFAR-10的分离结果进行定量评估。我们还为LSUN提供了定性的结果。
Despite substantial progress in signal source separation, results for richly structured data continue to contain perceptible artifacts. In contrast, recent deep generative models can produce authentic samples in a variety of domains that are indistinguishable from samples of the data distribution. This paper introduces a Bayesian approach to source separation that uses generative models as priors over the components of a mixture of sources, and noise-annealed Langevin dynamics to sample from the posterior distribution of sources given a mixture. This decouples the source separation problem from generative modeling, enabling us to directly use cutting-edge generative models as priors. The method achieves state-of-the-art performance for MNIST digit separation. We introduce new methodology for evaluating separation quality on richer datasets, providing quantitative evaluation of separation results on CIFAR-10. We also provide qualitative results on LSUN.
