Distributed Deep Joint Source-Channel Coding over a Multiple Access Channel

TL;DR

This paper introduces a novel non-orthogonal joint source-channel coding scheme for distributed image transmission over noisy multiple access channels, demonstrating significant quality improvements in practical finite block length scenarios.

Contribution

It proposes the first non-orthogonal JSCC scheme for distributed image transmission over MACs, outperforming existing orthogonal DeepJSCC methods in low bandwidth conditions.

Findings

Significant image quality improvements over orthogonal methods.

Effective non-orthogonal transmission in finite block length regimes.

Public release of source code for reproducibility.

Abstract

We consider distributed image transmission over a noisy multiple access channel (MAC) using deep joint source-channel coding (DeepJSCC). It is known that Shannon's separation theorem holds when transmitting independent sources over a MAC in the asymptotic infinite block length regime. However, we are interested in the practical finite block length regime, in which case separate source and channel coding is known to be suboptimal. We introduce a novel joint image compression and transmission scheme, where the devices send their compressed image representations in a non-orthogonal manner. While non-orthogonal multiple access (NOMA) is known to achieve the capacity region, to the best of our knowledge, non-orthogonal joint source channel coding (JSCC) scheme for practical systems has not been studied before. Through extensive experiments, we show significant improvements in terms of the quality of the reconstructed images compared to orthogonal transmission employing current DeepJSCC approaches particularly for low bandwidth ratios. We publicly share source code to facilitate further research and reproducibility.