Hyperparameter Learning of Stochastic Image Generative Models with Bayesian Hierarchical Modeling and Its Effect on Lossless Image Coding

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

Abstract

Explicit assumption of stochastic data generative models is a remarkable feature of lossless compression of general data in information theory. However, current lossless image coding mostly focus on coding procedures without explicit assumption of the stochastic generative model. Therefore, we have difficulty discussing the theoretical optimality of the coding procedure to the stochastic generative model. In this paper, we solve this difficulty by constructing a stochastic generative model by interpreting the previous coding procedure from another perspective. An important problem of our approach is how to learn the hyperparameters of the stochastic generative model because the optimality of our coding algorithm is guaranteed only asymptotically and the hyperparameter setting still affects the expected code length for finite length data. For this problem, we use Bayesian hierarchical modeling and confirm its effect by numerical experiments. In lossless image coding, this is the first study assuming such an explicit stochastic generative model and learning its hyperparameters, to the best of our knowledge.

Original languageEnglish
Title of host publication2021 IEEE Information Theory Workshop, ITW 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665403122
DOIs
Publication statusPublished - 2021
Event2021 IEEE Information Theory Workshop, ITW 2021 - Virtual, Online, Japan
Duration: 2021 Oct 172021 Oct 21

Publication series

Name2021 IEEE Information Theory Workshop, ITW 2021 - Proceedings

Conference

Conference2021 IEEE Information Theory Workshop, ITW 2021
Country/TerritoryJapan
CityVirtual, Online
Period21/10/1721/10/21

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Information Systems
  • Software

Fingerprint

Dive into the research topics of 'Hyperparameter Learning of Stochastic Image Generative Models with Bayesian Hierarchical Modeling and Its Effect on Lossless Image Coding'. Together they form a unique fingerprint.

Cite this