Source Separation with Deep Generative Priors
12. července 2020
Řečníci
Vivek Jayaram
Řečník · 0 sledujících
John Thickstun
Řečník · 0 sledujících
O prezentaci
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 deep generative models as priors over the components of a mixture of sources, and 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 and qualitative discussion of results for CIFAR-10 image separation.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 deep generative models as priors over the components of a mixture of sources, and Langevin dynamics to sample from the posterior…
Kategorie
Umělá inteligence a data science
Kategorie · 10,8k prezentací
O organizátorovi (ICML 2020)
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Generalisation error in learning with random features and the hidden manifold model
Zhlédnout později
Provable Self-Play Algorithms for Competitive Reinforcement Learning
Zhlédnout později
Yu Bai, …
When do ranking algorithms reinforce inequalities in social networks?
Zhlédnout později
Poster Session
Zhlédnout později
Shagun Uppal, …
Spectral Clustering with Graph Neural Networks for Graph Pooling
Zhlédnout později
Self-supervised Pitch Detection by Inverse Audio Synthesis
Zhlédnout později
Jesse Engel, …