Demo: Real-Time Semantic Communications with a Vision Transformer

Abstract

Semantic communications have shown promising advancements by optimizing source and channel coding jointly. However, the dynamics of these systems remain understudied, limiting research and performance gains. Inspired by the robustness of Vision Transformers (ViTs) in handling image nuisances, we propose a ViT-based model for semantic communications. Our approach achieves a peak signal-to-noise ratio (PSNR) gain of +0.5 dB over convolutional neural network variants. We introduce novel measures, average cosine similarity and Fourier analysis, to analyze the inner workings of semantic communications and optimize the system's performance. We also validate our approach through a real wireless channel prototype using software-defined radio (SDR). To the best of our knowledge, this is the first investigation of the fundamental workings of a semantic communications system, accompanied by the pioneering hardware implementation. To facilitate reproducibility and encourage further research, we provide open-source code, including neural network implementations and LabVIEW codes for SDRbased wireless transmission systems. 1

Semantic Communication: A Survey on Research Landscape, Challenges, and Future Directions

“…In light of the above-detailed realization challenges of Sem-Com, we refer the reader to the work in [362] that implements a real-time image SemCom system whose feasibility in actual wireless environments is demonstrated. Meanwhile, because challenges are always opportunities, some of the abovedetailed fundamental and major challenges of SemCom are also big opportunities for novel future directions of SemCom, as discussed below.…”