Vector Quantized Semantic Communication System

TL;DR

This paper introduces VQ-DeepSC, a deep learning-based vector quantized semantic communication system for images that enhances robustness and maintains high image quality in digital transmission.

Contribution

It develops a CNN-based transceiver with multi-scale semantic embedding and adversarial training, advancing digital semantic communication methods.

Findings

VQ-DeepSC outperforms BPG in robustness.

Achieves comparable MS-SSIM to DeepJSCC.

Uses adversarial training for improved image quality.

Abstract

Although analog semantic communication systems have received considerable attention in the literature, there is less work on digital semantic communication systems. In this paper, we develop a deep learning (DL)-enabled vector quantized (VQ) semantic communication system for image transmission, named VQ-DeepSC. Specifically, we propose a convolutional neural network (CNN)-based transceiver to extract multi-scale semantic features of images and introduce multi-scale semantic embedding spaces to perform semantic feature quantization, rendering the data compatible with digital communication systems. Furthermore, we employ adversarial training to improve the quality of received images by introducing a PatchGAN discriminator. Experimental results demonstrate that the proposed VQ-DeepSC is more robustness than BPG in digital communication systems and has comparable MS-SSIM performance to the DeepJSCC method.