Distributed Deep Joint Source-Channel Coding with Decoder-Only Side Information

TL;DR

A novel neural network architecture is proposed that incorporates the decoder-only side information at multiple stages at the receiver side, yielding improved performance at all channel conditions in terms of the various quality measures considered here, especially at low channel signal-to-noise ratios (SNRs) and small bandwidth ratios (BRs).

Abstract

We consider low-latency image transmission over a noisy wireless channel when correlated side information is present only at the receiver side (the Wyner-Ziv scenario). In particular, we are interested in developing practical schemes using a data-driven joint source-channel coding (JSCC) approach, which has been previously shown to outperform conventional separation-based approaches in the practical finite blocklength regimes, and to provide graceful degradation with channel quality. We propose a novel neural network architecture that incorporates the decoder-only side information at multiple stages at the receiver side. Our results demonstrate that the proposed method succeeds in integrating the side information, yielding improved performance at all channel conditions in terms of the various quality measures considered here, especially at low channel signal-to-noise ratios (SNRs) and small bandwidth ratios (BRs). We have made the source code of the proposed method public to enable further research, and the reproducibility of the results.

Figures (4)

• Figure 1: Separation-based (top) vs. JSCC-based (bottom) communication schemes, having decoder-only side information.
• Figure 2: Encoder architecture of our method (top), which is used to encode both the input image $\mathbf{x}$ at the transmitter and the side information image $\mathbf{x}_\mathrm{side}$ at the receiver side. Red arrows indicate the flow of the encoded side information. $\mathbf{s}_1$, $\mathbf{s}_2$, $\mathbf{s}_3$ and $\mathbf{s}_4$ denote the encoded side information at different scales, which are to be used at the receiver side. Decoder architecture of our method (bottom), which is used to reconstruct the input image from the noisy channel output $\mathbf{y}$ and the side information $\mathbf{x}_\mathrm{side}$.
• Figure 3: Visual comparison of reconstructed images from KITTIStereo (top) and Cityscape (bottom) datasets, having value of $\rho={1/32}$ and $\mathrm{SNR}_{\mathrm{test}}=-4$ dB.
• Figure 4: Comparison of the introduced DeepJSCC-WZ method with the baselines on the KITTIStereo and Cityscape datasets for $\rho \in \{1/16; 1/32\}$.