Variable rate deep image compression with modulated autoencoder
Yang, Fei (Centre de Visió per Computador (Bellaterra, Catalunya))
Herranz, Luis (Centre de Visió per Computador (Bellaterra, Catalunya))
Weijer, Joost van de (Centre de Visió per Computador (Bellaterra, Catalunya))
Iglesias-Guitian, Jose A. (Centre de Visió per Computador (Bellaterra, Catalunya))
López Peña, Antonio M. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Mozerov, Mikhail G. (Centre de Visió per Computador (Bellaterra, Catalunya))

Data:	2020
Descripció:	5 pàg.
Resum:	Variable rate is a requirement for flexible and adaptable image and video compression. However, deep image compression methods (DIC) are optimized for a single fixed rate-distortion (R-D) tradeoff. While this can be addressed by training multiple models for different tradeoffs, the memory requirements increase proportionally to the number of models. Scaling the bottleneck representation of a shared autoencoder can provide variable rate compression with a single shared autoencoder. However, the R-D performance using this simple mechanism degrades in low bitrates, and also shrinks the effective range of bitrates. To address these limitations, we formulate the problem of variable R-D optimization for DIC, and propose modulated autoencoders (MAEs), where the representations of a shared autoencoder are adapted to the specific R-D tradeoff via a modulation network. Jointly training this modulated autoencoder and the modulation network provides an effective way to navigate the R-D operational curve. Our experiments show that the proposed method can achieve almost the same R-D performance of independent models with significantly fewer parameters.
Ajuts:	European Commission 665919 Agencia Estatal de Investigación RTI2018-102285-A-I00 Agencia Estatal de Investigación TIN2017-88709-R Agencia Estatal de Investigación TIN2016-79717-R
Drets:	Tots els drets reservats.
Llengua:	Anglès
Document:	Article ; recerca ; Versió acceptada per publicar
Matèria:	Bit rate ; Decoding ; Training ; Image coding ; Distortion ; Quantization (signal) ; Adaptation models
Publicat a:	IEEE signal processing letters, Vol. 27 (2020) , p. 331-335, ISSN 1070-9908

DOI: 10.1109/LSP.2020.2970539

Postprint 6 p, 3.0 MB

El registre apareix a les col·leccions:
Articles > Articles de recerca
Articles > Articles publicats