Semantic-oriented communication has been considered as a promising to boost the bandwidth efficiency by only transmitting the semantics of the data. In this paper, we propose a multi-level semantic aware communication system for wireless image transmission, named MLSC-image, which is based on the deep learning techniques and trained in an end to end manner. In particular, the proposed model includes a multilevel semantic feature extractor, that extracts both the highlevel semantic information, such as the text semantics and the segmentation semantics, and the low-level semantic information, such as local spatial details of the images. We employ a pretrained image caption to capture the text semantics and a pretrained image segmentation model to obtain the segmentation semantics. These high-level and low-level semantic features are then combined and encoded by a joint semantic and channel encoder into symbols to transmit over the physical channel. The numerical results validate the effectiveness and efficiency of the proposed semantic communication system, especially under the limited bandwidth condition, which indicates the advantages of the high-level semantics in the compression of images.

翻译：面向语义的通信被认为是一种有前景的技术，仅通过传输数据的语义即可提升带宽效率。本文提出一种基于深度学习技术并以端到端方式训练的无线图像传输多级语义感知通信系统，命名为MLSC-image。具体而言，所提模型包含一个多级语义特征提取器，可提取高级语义信息（如文本语义与分割语义）以及低级语义信息（如图像局部空间细节）。我们采用预训练图像描述模型捕获文本语义，并利用预训练图像分割模型获取分割语义。这些高低级语义特征随后通过联合语义与信道编码器组合并编码为符号，经物理信道传输。数值结果验证了所提语义通信系统的有效性和效率，尤其在带宽受限条件下，表明高级语义在图像压缩中的优势。