Distributed Deep Joint Source-Channel Coding over a Multiple Access Channel
This addresses the problem of efficient image transmission in practical communication systems, representing an incremental advance by applying non-orthogonal techniques to joint source-channel coding.
The paper tackles distributed image transmission over a noisy multiple access channel in the finite block length regime by introducing a non-orthogonal joint source-channel coding scheme, showing significant improvements in reconstructed image quality, especially at low bandwidth ratios, compared to existing orthogonal methods.
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.