Neural Distributed Source Coding

We consider the Distributed Source Coding (DSC) problem concerning the task of encoding an input in the absence of correlated side information that is only available to the decoder. Remarkably, Slepian and Wolf showed in 1973 that an encoder without access to the side information can asymptotically...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE journal on selected areas in information theory Jg. 5; S. 493 - 508
Hauptverfasser: Whang, Jay, Nagle, Alliot, Acharya, Anish, Kim, Hyeji, Dimakis, Alexandros G.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Autoencoders
Berger-Tung inner bound
Coders
Correlation
Datasets
Decoding
Distributed management
Distributed source coding
Image coding
Image reconstruction
Information theory
Slepian-Wolf coding
Source coding
State-of-the-art reviews
Synthetic data
Training
vector-quantized variational auto-encoder
Vectors
Wynzer-Ziv coding
ISSN:2641-8770, 2641-8770
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We consider the Distributed Source Coding (DSC) problem concerning the task of encoding an input in the absence of correlated side information that is only available to the decoder. Remarkably, Slepian and Wolf showed in 1973 that an encoder without access to the side information can asymptotically achieve the same compression rate as when the side information is available to it. This seminal result was later extended to lossy compression of distributed sources by Wyner, Ziv, Berger, and Tung. While there is vast prior work on this topic, practical DSC has been limited to synthetic datasets and specific correlation structures. Here we present a framework for lossy DSC that is agnostic to the correlation structure and can scale to high dimensions. Rather than relying on hand-crafted source modeling, our method utilizes a conditional Vector-Quantized Variational auto-encoder (VQ-VAE) to learn the distributed encoder and decoder. We evaluate our method on multiple datasets and show that our method can handle complex correlations and achieves state-of-the-art PSNR.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2641-8770
2641-8770
DOI:10.1109/JSAIT.2024.3412976