# WITT: A Wireless Image Transmission Transformer for Semantic Communications

arXiv: https://arxiv.org/abs/2211.00937 · HTML: https://mlsanity.com/paper/2211.00937/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 2 Nov 2022.

## Builds on (most cited first, 7 of 7)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Deep Learning Enabled Semantic Communication Systems](https://mlsanity.com/paper/2006.10685/) (2020)
- [DeepJSCC-f: Deep Joint Source-Channel Coding of Images with Feedback](https://mlsanity.com/paper/1911.11174/) (2019)
- [Deep Learning for Joint Source-Channel Coding of Text](https://mlsanity.com/paper/1802.06832/) (2018)
- [Wireless Image Retrieval at the Edge](https://mlsanity.com/paper/2007.10915/) (2020)
- [Perceptual Learned Source-Channel Coding for High-Fidelity Image Semantic Transmission](https://mlsanity.com/paper/2205.13120/) (2022)

## Built on by (most cited first, 30 of 37)

- [CDDM: Channel Denoising Diffusion Models for Wireless Semantic Communications](https://mlsanity.com/paper/2309.08895/) (2023)
- [CDDM: Channel Denoising Diffusion Models for Wireless Communications](https://mlsanity.com/paper/2305.09161/) (2023)
- [Visual Language Model based Cross-modal Semantic Communication Systems](https://mlsanity.com/paper/2407.00020/) (2024)
- [Diffusion-Aided Joint Source Channel Coding For High Realism Wireless Image Transmission](https://mlsanity.com/paper/2404.17736/) (2024)
- [Robust Image Semantic Coding with Learnable CSI Fusion Masking over MIMO Fading Channels](https://mlsanity.com/paper/2406.07389/) (2024)
- [Semantic Successive Refinement: A Generative AI-aided Semantic Communication Framework](https://mlsanity.com/paper/2408.05112/) (2024)
- [Segment Anything Meets Semantic Communication](https://mlsanity.com/paper/2306.02094/) (2023)
- [Importance-Aware Image Segmentation-based Semantic Communication for Autonomous Driving](https://mlsanity.com/paper/2401.10153/) (2024)
- [DM-MIMO: Diffusion Models for Robust Semantic Communications over MIMO Channels](https://mlsanity.com/paper/2407.05289/) (2024)
- [Generative Semantic Communication for Joint Image Transmission and Segmentation](https://mlsanity.com/paper/2411.18005/) (2024)
- [DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey](https://mlsanity.com/paper/2503.09956/) (2025)
- [An Efficient Federated Learning Framework for Training Semantic Communication System](https://mlsanity.com/paper/2310.13236/) (2023)
- [Multi-user Wireless Image Semantic Transmission over MIMO Multiple Access Channels](https://mlsanity.com/paper/2504.07969/) (2025)
- [Transformer-Aided Semantic Communications](https://mlsanity.com/paper/2405.01521/) (2024)
- [Efficient Semantic Communication Through Transformer-Aided Compression](https://mlsanity.com/paper/2412.01817/) (2024)
- [Semantic Edge-Cloud Communication for Real-Time Urban Traffic Surveillance with ViT and LLMs over Mobile Networks](https://mlsanity.com/paper/2509.21259/) (2025)
- [Semantic Multi-Resolution Communications](https://mlsanity.com/paper/2308.11604/) (2023)
- [FSSC: Federated Learning of Transformer Neural Networks for Semantic Image Communication](https://mlsanity.com/paper/2407.21507/) (2024)
- [From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications](https://mlsanity.com/paper/2505.22311/) (2025)
- [SC-CDM: Enhancing Quality of Image Semantic Communication with a Compact Diffusion Model](https://mlsanity.com/paper/2410.02121/) (2024)
- [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)
- [Wireless Video Semantic Communication with Decoupled Diffusion Multi-frame Compensation](https://mlsanity.com/paper/2511.02478/) (2025)
- [Scenario-Adaptive MU-MIMO OFDM Semantic Communication With Asymmetric Neural Network](https://mlsanity.com/paper/2602.13557/) (2026)
- [Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models](https://mlsanity.com/paper/2604.26508/) (2026)
- [Interplay of Semantic Communication and Knowledge Learning](https://mlsanity.com/paper/2402.03339/) (2024)
- [Learnable Residual-Based Latent Denoising in Semantic Communication](https://mlsanity.com/paper/2502.07319/) (2025)
- [Semantic Communication in Dynamic Channel Scenarios: Collaborative Optimization of Dual-Pipeline Joint Source-Channel Coding and Personalized Federated Learning](https://mlsanity.com/paper/2503.14084/) (2025)
- [TOAST: Task-Oriented Adaptive Semantic Transmission over Dynamic Wireless Environments](https://mlsanity.com/paper/2506.21900/) (2025)
- [Way to Build Native AI-driven 6G Air Interface: Principles, Roadmap, and Outlook](https://mlsanity.com/paper/2508.15277/) (2025)

## Abstract (arXiv)

In this paper, we aim to redesign the vision Transformer (ViT) as a new backbone to realize semantic image transmission, termed wireless image transmission transformer (WITT). Previous works build upon convolutional neural networks (CNNs), which are inefficient in capturing global dependencies, resulting in degraded end-to-end transmission performance especially for high-resolution images. To tackle this, the proposed WITT employs Swin Transformers as a more capable backbone to extract long-range information. Different from ViTs in image classification tasks, WITT is highly optimized for image transmission while considering the effect of the wireless channel. Specifically, we propose a spatial modulation module to scale the latent representations according to channel state information, which enhances the ability of a single model to deal with various channel conditions. As a result, extensive experiments verify that our WITT attains better performance for different image resolutions, distortion metrics, and channel conditions. The code is available at https://github.com/KeYang8/WITT.