DRASIC: Distributed Recurrent Autoencoder for Scalable Image Compression
This work addresses scalable and efficient image compression for applications requiring low power, robustness, and data privacy, representing a novel data-driven approach to distributed source coding.
The paper tackles distributed image compression from multiple correlated sources by proposing DRASIC, a distributed recurrent autoencoder architecture that trains separate encoders and a joint decoder, achieving performance within 2 dB PSNR of a single centralized codec and outperforming separately trained codecs.
We propose a new architecture for distributed image compression from a group of distributed data sources. The work is motivated by practical needs of data-driven codec design, low power consumption, robustness, and data privacy. The proposed architecture, which we refer to as Distributed Recurrent Autoencoder for Scalable Image Compression (DRASIC), is able to train distributed encoders and one joint decoder on correlated data sources. Its compression capability is much better than the method of training codecs separately. Meanwhile, the performance of our distributed system with 10 distributed sources is only within 2 dB peak signal-to-noise ratio (PSNR) of the performance of a single codec trained with all data sources. We experiment distributed sources with different correlations and show how our data-driven methodology well matches the Slepian-Wolf Theorem in Distributed Source Coding (DSC). To the best of our knowledge, this is the first data-driven DSC framework for general distributed code design with deep learning.