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

TL;DR

This paper introduces SNR-EQ-JSCC, a lightweight, channel-adaptive semantic coding architecture based on Transformers that enhances image transmission over dynamic channels by embedding SNR information into attention mechanisms, outperforming existing methods.

Contribution

The paper proposes a novel Transformer-based JSCC model that adaptively incorporates SNR feedback into attention scores for improved robustness and performance in semantic communication systems.

Findings

Outperforms SwinJSCC in PSNR and perception metrics.

Requires minimal storage and computational overhead for channel adaptation.

Effective even with only average SNR feedback, without retraining.

Abstract

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.