TY  - JOUR
AU  - Fei Yang
AU  - Luis Herranz
AU  - Joost Van de Weijer
AU  - Jose Antonio Iglesias
AU  - Antonio Lopez
AU  - Mikhail Mozerov
PY  - 2020//
TI  - Variable Rate Deep Image Compression with Modulated Autoencoder
T2  - SPL
JO  - IEEE Signal Processing Letters
SP  - 331
EP  - 335
VL  - 27
N2  - 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.
UR  - https://ieeexplore.ieee.org/document/8977394
L1  - http://refbase.cvc.uab.es/files/YHW2020.pdf
UR  - http://dx.doi.org/10.1109/LSP.2020.2970539
N1  - LAMP; ADAS; 600.141; 600.120; 600.118
ID  - Fei Yang2020
ER  -