%0 Journal Article %T Variable Rate Deep Image Compression with Modulated Autoencoder %A Fei Yang %A Luis Herranz %A Joost Van de Weijer %A Jose Antonio Iglesias %A Antonio Lopez %A Mikhail Mozerov %J IEEE Signal Processing Letters %D 2020 %V 27 %F Fei Yang2020 %O LAMP; ADAS; 600.141; 600.120; 600.118 %O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3346), last updated on Fri, 07 Jan 2022 12:29:16 +0100 %X 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. %U https://ieeexplore.ieee.org/document/8977394 %U http://refbase.cvc.uab.es/files/YHW2020.pdf %U http://dx.doi.org/10.1109/LSP.2020.2970539 %P 331-335