Deep Joint Source-Channel Coding of Images with Feedback
David Burth Kurka, Denız Gündüz
Abstract
We consider wireless transmission of images in the presence of channel output feedback, by introducing an autoencoder-based deep joint source-channel coding (JSCC) scheme. We achieve impressive results in terms of the end-to-end reconstruction quality for fixed length transmission, and in terms of the average delay for variable length transmission. To the best of our knowledge, this is the first practical JSCC scheme that can fully exploit channel output feedback, demonstrating yet another setting in which modern machine learning techniques can enable the design of new and efficient communication methods that surpass the performance of traditional structured coding schemes.
Topics & Concepts
Computer scienceExploitCoding (social sciences)AutoencoderChannel (broadcasting)Joint (building)WirelessTransmission (telecommunications)Channel codeDecoding methodsArtificial intelligenceEncoderDeep learningAlgorithmComputer engineeringTheoretical computer scienceComputer networkTelecommunicationsMathematicsEngineeringComputer securityArchitectural engineeringOperating systemStatisticsAdvanced Data Compression TechniquesWireless Communication Security TechniquesWireless Signal Modulation Classification