# SwinJSCC: Taming Swin Transformer for Deep Joint Source-Channel Coding

arXiv: https://arxiv.org/abs/2308.09361 · HTML: https://mlsanity.com/paper/2308.09361/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2023.

## Built on by (most cited first, 30 of 45)

- [Adaptive Semantic Token Communication for Transformer-based Edge Inference](https://mlsanity.com/paper/2505.17604/) (2025)
- [Diffusion-Aided Joint Source Channel Coding For High Realism Wireless Image Transmission](https://mlsanity.com/paper/2404.17736/) (2024)
- [Token Communication in the Era of Large Models: An Information Bottleneck-Based Approach](https://mlsanity.com/paper/2507.01728/) (2025)
- [Agent-driven Generative Semantic Communication with Cross-Modality and Prediction](https://mlsanity.com/paper/2404.06997/) (2024)
- [Adaptive Token Merging for Efficient Transformer Semantic Communication at the Edge](https://mlsanity.com/paper/2509.09955/) (2025)
- [MambaJSCC: Adaptive Deep Joint Source-Channel Coding with Generalized State Space Model](https://mlsanity.com/paper/2409.16592/) (2024)
- [ICDM: Interference Cancellation Diffusion Models for Wireless Semantic Communications](https://mlsanity.com/paper/2505.19983/) (2025)
- [Learned Image Transmission with Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2408.16340/) (2024)
- [Deep Learning-Based Image Compression for Wireless Communications: Impacts on Reliability,Throughput, and Latency](https://mlsanity.com/paper/2411.10650/) (2024)
- [Enabling Training-Free Semantic Communication Systems with Generative Diffusion Models](https://mlsanity.com/paper/2505.01209/) (2025)
- [Conquering High Packet-Loss Erasure: MoE Swin Transformer-Based Video Semantic Communication](https://mlsanity.com/paper/2508.01205/) (2025)
- [SNR-EQ-JSCC: Joint Source-Channel Coding with SNR-Based Embedding and Query](https://mlsanity.com/paper/2501.04732/) (2025)
- [Modeling and Performance Analysis for Semantic Communications Based on Empirical Results](https://mlsanity.com/paper/2504.21055/) (2025)
- [SecDiff: Diffusion-Aided Secure Deep Joint Source-Channel Coding Against Adversarial Attacks](https://mlsanity.com/paper/2511.01466/) (2025)
- [Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications](https://mlsanity.com/paper/2511.08416/) (2025)
- [DiT-JSCC: Rethinking Deep JSCC with Diffusion Transformers and Semantic Representations](https://mlsanity.com/paper/2601.03112/) (2026)
- [Scenario-Adaptive MU-MIMO OFDM Semantic Communication With Asymmetric Neural Network](https://mlsanity.com/paper/2602.13557/) (2026)
- [TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems](https://mlsanity.com/paper/2605.21553/) (2026)
- [Ada-TokenCom: Rate-Adaptive Token Communications via Large-Model-Driven Token Compression and Generation](https://mlsanity.com/paper/2608.28086/) (2026)
- [Object-Attribute-Relation Representation Based Video Semantic Communication](https://mlsanity.com/paper/2406.10469/) (2024)
- [Two Birds with One Stone: Multi-Task Semantic Communications Systems over Relay Channel](https://mlsanity.com/paper/2410.12302/) (2024)
- [Knowledge-Base based Semantic Image Transmission Using CLIP](https://mlsanity.com/paper/2504.01053/) (2025)
- [Latent Diffusion Model Based Denoising Receiver for 6G Semantic Communication: From Stochastic Differential Theory to Application](https://mlsanity.com/paper/2506.05710/) (2025)
- [TOAST: Task-Oriented Adaptive Semantic Transmission over Dynamic Wireless Environments](https://mlsanity.com/paper/2506.21900/) (2025)
- [VQ-DeepISC: Vector Quantized-Enabled Digital Semantic Communication with Channel Adaptive Image Transmission](https://mlsanity.com/paper/2508.03740/) (2025)
- [Way to Build Native AI-driven 6G Air Interface: Principles, Roadmap, and Outlook](https://mlsanity.com/paper/2508.15277/) (2025)
- [SemSteDiff: Generative Diffusion Model-based Coverless Semantic Steganography Communication](https://mlsanity.com/paper/2509.04803/) (2025)
- [Context Video Semantic Transmission with Variable Length and Rate Coding over MIMO Channels](https://mlsanity.com/paper/2601.06059/) (2025)
- [VQ-DSC-R: Robust Vector Quantized-Enabled Digital Semantic Communication With OFDM Transmission](https://mlsanity.com/paper/2602.15045/) (2026)
- [SAFT: Sensitivity-Aware Filtering and Transmission for Adaptive 3D Point Cloud Communication over Wireless Channels](https://mlsanity.com/paper/2603.26197/) (2026)

## Abstract (arXiv)

As one of the key techniques to realize semantic communications, end-to-end optimized neural joint source-channel coding (JSCC) has made great progress over the past few years. A general trend in many recent works pushing the model adaptability or the application diversity of neural JSCC is based on the convolutional neural network (CNN) backbone, whose model capacity is yet limited, inherently leading to inferior system coding gain against traditional coded transmission systems. In this paper, we establish a new neural JSCC backbone that can also adapt flexibly to diverse channel conditions and transmission rates within a single model, our open-source project aims to promote the research in this field. Specifically, we show that with elaborate design, neural JSCC codec built on the emerging Swin Transformer backbone achieves superior performance than conventional neural JSCC codecs built upon CNN, while also requiring lower end-to-end processing latency. Paired with two spatial modulation modules that scale latent representations based on the channel state information and target transmission rate, our baseline SwinJSCC can further upgrade to a versatile version, which increases its capability to adapt to diverse channel conditions and rate configurations. Extensive experimental results show that our SwinJSCC achieves better or comparable performance versus the state-of-the-art engineered BPG + 5G LDPC coded transmission system with much faster end-to-end coding speed, especially for high-resolution images, in which case traditional CNN-based JSCC yet falls behind due to its limited model capacity.