Source Separation with Deep Generative Priors
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. T...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | 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. |
---|---|
DOI: | 10.48550/arxiv.2002.07942 |