Channel-Adaptive Wireless Image Semantic Transmission with Learnable Prompts

TL;DR

This paper introduces PJSCC, a DeepJSCC framework with learnable prompts that adapt to varying wireless channel conditions, improving image transmission quality without retraining across different scenarios.

Contribution

The paper proposes a novel DeepJSCC method using learnable prompts to implicitly incorporate channel state information, enabling dynamic adaptation to diverse wireless channel conditions.

Findings

PJSCC outperforms existing DeepJSCC methods in PSNR and LPIPS metrics across various SNRs.

PJSCC demonstrates strong generalization to different channel models without retraining.

The approach is resource-efficient and suitable for deployment on constrained devices.

Abstract

Recent developments in Deep learning based Joint Source-Channel Coding (DeepJSCC) have demonstrated impressive capabilities within wireless semantic communications system. However, existing DeepJSCC methodologies exhibit limited generalization ability across varying channel conditions, necessitating the preparation of multiple models. Optimal performance is only attained when the channel status during testing aligns precisely with the training channel status, which is very inconvenient for real-life applications. In this paper, we introduce a novel DeepJSCC framework, termed Prompt JSCC (PJSCC), which incorporates a learnable prompt to implicitly integrate the physical channel state into the transmission system. Specifically, the Channel State Prompt (CSP) module is devised to generate prompts based on diverse SNR and channel distribution models. Through the interaction of latent image features with channel features derived from the CSP module, the DeepJSCC process dynamically adapts to varying channel conditions without necessitating retraining. Comparative analyses against leading DeepJSCC methodologies and traditional separate coding approaches reveal that the proposed PJSCC achieves optimal image reconstruction performance across different SNR settings and various channel models, as assessed by Peak Signal-to-Noise Ratio (PSNR) and Learning-based Perceptual Image Patch Similarity (LPIPS) metrics. Furthermore, in real-world scenarios, PJSCC shows excellent memory efficiency and scalability, rendering it readily deployable on resource-constrained platforms to facilitate semantic communications.