Deep Joint Source-Channel Coding for Wireless Image Transmission
arXiv:1809.01733 · doi:10.1109/TCCN.2019.2919300
Abstract
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.
To appear in IEEE Transactions on Cognitive Communications and Networking
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- End-to-end Optimized Image Compression
- Deep Learning Methods for Improved Decoding of Linear Codes
- Deep Learning Based MIMO Communications
- SparseCast: Hybrid Digital-Analog Wireless Image Transmission Exploiting Frequency Domain Sparsity
Cited by in corpus (74)
- Deep Learning Enabled Semantic Communication Systems
- Wireless Image Transmission Using Deep Source Channel Coding With Attention Modules
- Resource allocation for text semantic communications
- Networking Architecture and Key Supporting Technologies for Human Digital Twin in Personalized Healthcare: A Comprehensive Survey
- Deep Source-Channel Coding for Sentence Semantic Transmission with HARQ
- Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities
- Heterogeneous Semantic and Bit Communications: A Semi-NOMA Scheme
- Rethinking Modern Communication from Semantic Coding to Semantic Communication
- Vector Quantized Semantic Communication System
- Joint Device-Edge Inference over Wireless Links with Pruning
- Exploiting Semantic Communication for Non-Orthogonal Multiple Access
- Channel-Adaptive Wireless Image Transmission with OFDM
- Non-Orthogonal Multiple Access Enhanced Multi-User Semantic Communication
- One-to-Many Semantic Communication Systems: Design, Implementation, Performance Evaluation
- Meta-Learning to Communicate: Fast End-to-End Training for Fading Channels
- Deep Joint Source-Channel Coding for Wireless Image Retrieval
- Probabilistic Semantic Communication over Wireless Networks with Rate Splitting
- On the Role of ViT and CNN in Semantic Communications: Analysis and Prototype Validation
- Swin Transformer-Based Dynamic Semantic Communication for Multi-User with Different Computing Capacity
- Deep Learning in Physical Layer: Review on Data Driven End-to-End Communication Systems and their Enabling Semantic Applications
- Towards Goal-Oriented Semantic Communications: New Metrics, Framework, and Open Challenges
- An Efficient Federated Learning Framework for Training Semantic Communication System
- Distributed satellite information networks: Architecture, enabling technologies, and trends
- Semantic Information Recovery in Wireless Networks
- Constellation Design for Deep Joint Source-Channel Coding
- High Perceptual Quality Wireless Image Delivery with Denoising Diffusion Models
- A Joint Communication and Computation Design for Semantic Wireless Communication with Probability Graph
- Latent Diffusion Model-Enabled Low-Latency Semantic Communication in the Presence of Semantic Ambiguities and Wireless Channel Noises
- Multi-Task Semantic Communication With Graph Attention-Based Feature Correlation Extraction
- A Specific Task-oriented Semantic Image Communication System for substation patrol inspection
- Two-Way Semantic Transmission of Images without Feedback
- Semantic Edge Computing and Semantic Communications in 6G Networks: A Unifying Survey and Research Challenges
- Towards Effective and Interpretable Semantic Communications
- Optimizing Multi-User Semantic Communication via Transfer Learning and Knowledge Distillation
- Semantic Communication Enabled 6G-NTN Framework: A Novel Denoising and Gateway Hop Integration Mechanism
- Explicit Semantic-Base-Empowered Communications for 6G Mobile Networks
- Neural Network Coding
- Atmospheric Turbulence-Immune Free Space Optical Communication System based on Discrete-Time Analog Transmission
- Deep Joint Source Channel Coding for WirelessImage Transmission with OFDM
- Information Bottleneck-Inspired Type Based Multiple Access for Remote Estimation in IoT Systems
- Transmit What You Need: Task-Adaptive Semantic Communications for Visual Information
- Bridging Neural Networks and Wireless Systems with MIMO-OFDM Semantic Communications
- Semantic Communication Systems for Speech Transmission
- A Very Brief Introduction to Machine Learning With Applications to Communication Systems
- Low density majority codes and the problem of graceful degradation
- Data-Importance Aware User Scheduling for Communication-Efficient Edge Machine Learning
- Region-of-Interest-Guided Deep Joint Source-Channel Coding for Image Transmission
- Internet of Things (IoT) Connectivity in 6G: An Interplay of Time, Space, Intelligence, and Value
- Joint Source-and-Channel Coding for Small Satellite Applications
- Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach
- Blind interactive learning of modulation schemes: Multi-agent cooperation without co-design
- An Introduction to Communication Efficient Edge Machine Learning
- Design of Capacity-Approaching Low-Density Parity-Check Codes using Recurrent Neural Networks
- Quantum-Classical Autoencoder Architectures for End-to-End Radio Communication
- Semantic Feature Division Multiple Access for Digital Semantic Broadcast Channels
- Topological Neural Networks over the Air
- A Variational Auto-Encoder Approach for Image Transmission in Wireless Channel
- On Learning-Assisted Content-Based Secure Image Transmission for Delay-Aware Systems with Randomly-Distributed Eavesdroppers -- Extended Version
- Deep Joint Source-Channel Coding for Multi-Task Network
- LoRa Modulation for Split Learning
- Branchy-GNN: a Device-Edge Co-Inference Framework for Efficient Point Cloud Processing
- Eavesdropping on Goal-Oriented Communication: Timing Attacks and Countermeasures
- Deep Joint Transmission-Recognition for Multi-View Cameras
- Neural Communication Systems with Bandwidth-limited Channel
- Reinforcement-Learned Unequal Error Protection for Quantized Semantic Embeddings
- Foundation Models for Generalizable Semantic and Goal-Oriented Communication
- Knowledge-Base based Semantic Image Transmission Using CLIP
- Semantic Communications for Speech Recognition
- Adversarial Jamming for Autoencoder Distribution Matching
- DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey
- Robustness in Wireless Distributed Learning: An Information-Theoretic Analysis
- Efficient Transmission of Radiomaps via Physics-Enhanced Semantic Communications
- On Low Density Majority Codes
- SNR-adaptive deep joint source-channel coding for wireless image transmission