Research Repository

Deep Joint Source-Channel Coding for Wireless Image Transmission

Bourtsoulatze, Eirina and Burth Kurka, David and Gunduz, Deniz (2019) 'Deep Joint Source-Channel Coding for Wireless Image Transmission.' IEEE Transactions on Cognitive Communications and Networking, 5 (3). pp. 567-579. ISSN 2332-7731

FINAL VERSION.pdf - Accepted Version

Download (18MB) | Preview


We propose a joint source and channel coding (JSCC) technique for wireless image transmission that does not rely on explicit codes for either compression or error correction; instead, it directly maps the image pixel values to the complex-valued channel input symbols. We parameterize the encoder and decoder functions by two convolutional neural networks (CNNs), which are trained jointly, and can be considered as an autoencoder with a non-trainable layer in the middle that represents the noisy communication channel. Our results show that the proposed deep JSCC scheme outperforms digital transmission concatenating JPEG or JPEG2000 compression with a capacity achieving channel code at low signal-to-noise ratio (SNR) and channel bandwidth values in the presence of additive white Gaussian noise (AWGN). More strikingly, deep JSCC does not suffer from the “cliff effect,” and it provides a graceful performance degradation as the channel SNR varies with respect to the SNR value assumed during training. In the case of a slow Rayleigh fading channel, deep JSCC learns noise resilient coded representations and significantly outperforms separation-based digital communication at all SNR and channel bandwidth values.

Item Type: Article
Divisions: Faculty of Science and Health
Faculty of Science and Health > Computer Science and Electronic Engineering, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 20 May 2020 16:40
Last Modified: 15 Jan 2022 01:32

Actions (login required)

View Item View Item