Source Separation with Deep Generative Priors

被引:0
|
作者
Jayaram, Vivek [1 ]
Thickstun, John [1 ]
机构
[1] Univ Washington, Paul G Allen Sch Comp Sci & Engn, Seattle, WA 98195 USA
基金
美国国家科学基金会;
关键词
BLIND SOURCE SEPARATION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页数:12
相关论文
共 50 条
  • [21] Solution of physics-based Bayesian inverse problems with deep generative priors
    Patel, Dhruv, V
    Ray, Deep
    Oberai, Assad A.
    COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2022, 400
  • [22] Reverberant Source Separation Using NTF With Delayed Subsources and Spatial Priors
    Fras, Mieszko
    Kowalczyk, Konrad
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2024, 32 : 1954 - 1967
  • [23] Compressed Sensing-Based Robust Phase Retrieval via Deep Generative Priors
    Shamshad, Fahad
    Ahmed, Ali
    IEEE SENSORS JOURNAL, 2021, 21 (02) : 2286 - 2298
  • [24] Blind Single Image Reflection Suppression for Face Images using Deep Generative Priors
    Chandramouli, Paramanand
    Gandikota, Kanchana Vaishnavi
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 3315 - 3323
  • [25] Misspecified Phase Retrieval with Generative Priors
    Liu, Zhaoqiang
    Wang, Xinshao
    Liu, Jiulong
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [26] SINGLE IMAGE RESTORATION WITH GENERATIVE PRIORS
    Basioti, Kalliopi
    Moustakides, George, V
    2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 1679 - 1683
  • [27] The Spiked Matrix Model With Generative Priors
    Aubin, Benjamin
    Loureiro, Bruno
    Maillard, Antoine
    Krzakala, Florent
    Zdeborova, Lenka
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2021, 67 (02) : 1156 - 1181
  • [28] The spiked matrix model with generative priors
    Aubin, Benjamin
    Loureiro, Bruno
    Maillard, Antoine
    Krzakala, Florent
    Zdeborova, Lenka
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [29] Toward deep drum source separation
    Mezza, Alessandro Ilic
    Giampiccolo, Riccardo
    Bernardini, Alberto
    Sarti, Augusto
    PATTERN RECOGNITION LETTERS, 2024, 183 : 86 - 91
  • [30] DEEP UNFOLDING FOR MULTICHANNEL SOURCE SEPARATION
    Wisdom, Scott
    Hershey, John
    Le Roux, Jonathan
    Watanabe, Shinji
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 121 - 125