# SNR-EQ-JSCC: Joint Source-Channel Coding with SNR-Based Embedding and Query

arXiv: https://arxiv.org/abs/2501.04732 · HTML: https://mlsanity.com/paper/2501.04732/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 7 Jan 2025.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [DeepJSCC-f: Deep Joint Source-Channel Coding of Images with Feedback](https://mlsanity.com/paper/1911.11174/) (2019)
- [Nonlinear Transform Source-Channel Coding for Semantic Communications](https://mlsanity.com/paper/2112.10961/) (2021)
- [Task-Oriented Multi-User Semantic Communications for VQA Task](https://mlsanity.com/paper/2108.07357/) (2021)
- [SwinJSCC: Taming Swin Transformer for Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2308.09361/) (2023)
- [Channel-Adaptive Wireless Image Transmission with OFDM](https://mlsanity.com/paper/2205.02417/) (2022)
- [Transformer-aided Wireless Image Transmission with Channel Feedback](https://mlsanity.com/paper/2306.09101/) (2023)
- [DeepJSCC-l++: Robust and Bandwidth-Adaptive Wireless Image Transmission](https://mlsanity.com/paper/2305.13161/) (2023)
- [Semantic Importance-Aware Based for Multi-User Communication Over MIMO Fading Channels](https://mlsanity.com/paper/2312.16057/) (2023)

## Built on by (most cited first, 1 of 1)

- [Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts Mechanism](https://mlsanity.com/paper/2604.02691/) (2026)

## Abstract (arXiv)

Coping with the impact of dynamic channels is a critical issue in joint source-channel coding (JSCC)-based semantic communication systems. In this paper, we propose a lightweight channel-adaptive semantic coding architecture called SNR-EQ-JSCC. It is built upon the generic Transformer model and achieves channel adaptation (CA) by Embedding the signal-to-noise ratio (SNR) into the attention blocks and dynamically adjusting attention scores through channel-adaptive Queries. Meanwhile, penalty terms are introduced in the loss function to stabilize the training process. Considering that instantaneous SNR feedback may be imperfect, we propose an alternative method that uses only the average SNR, which requires no retraining of SNR-EQ-JSCC. Simulation results conducted on image transmission demonstrate that the proposed SNR-EQJSCC outperforms the state-of-the-art SwinJSCC in peak signal-to-noise ratio (PSNR) and perception metrics while only requiring 0.05% of the storage overhead and 6.38% of the computational complexity for CA. Moreover, the channel-adaptive query method demonstrates significant improvements in perception metrics. When instantaneous SNR feedback is imperfect, SNR-EQ-JSCC using only the average SNR still surpasses baseline schemes.