Perception-Distortion Trade-Off with Restricted Boltzmann Machines

Chris Cannella, Jie DIng, Mohammadreza Soltani, Yi Zhou, Vahid Tarokh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work, we introduce a new procedure for applying Restricted Boltzmann Machines (RBMs) to missing data inference tasks, based on linearization of the effective energy function governing the distribution of observations. We compare the performance of our proposed procedure with those obtained using existing reconstruction procedures trained on incomplete data. We place these performance comparisons within the context of the perception-distortion trade-off observed in other data reconstruction tasks, which has, until now, remained unexplored in tasks relying on incomplete training data.

Original languageEnglish (US)
Title of host publication2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4022-4026
Number of pages5
ISBN (Electronic)9781509066315
DOIs
StatePublished - May 2020
Event2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain
Duration: May 4 2020May 8 2020

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2020-May
ISSN (Print)1520-6149

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
CountrySpain
CityBarcelona
Period5/4/205/8/20

Bibliographical note

Funding Information:
This work was supported in part by the Office of Naval Research Grant No. N00014-18-1-2244 and DARPA Grant No. HR00111890040.

Keywords

  • Generative Models
  • Imputation
  • Missing Data
  • Perception-Distortion Trade-off
  • Restricted Boltzmann Machine

Fingerprint Dive into the research topics of 'Perception-Distortion Trade-Off with Restricted Boltzmann Machines'. Together they form a unique fingerprint.

Cite this