SNR-adaptive deep joint source-channel coding scheme for image semantic transmission with convolutional block attention module

作     者：Yang Yujia Liu Yiming Zhang Wenjia Zhang Zhi Yang Yujia;Liu Yiming;Zhang Wenjia;Zhang Zhi

作者机构：State Key Laboratory of Networking and Switch TechnologyBeijing University of Posts and TelecommunicationsBeijing 100876China 

出 版 物：《The Journal of China Universities of Posts and Telecommunications》 (中国邮电高校学报（英文版）)

年 卷 期：2024年第31卷第1期

页      面：1-11页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 070104[理学-应用数学] 0835[工学-软件工程] 081101[工学-控制理论与控制工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was supported in part by the National Natural Science Foundation of China(62293481) in part by the Young Elite Scientists Sponsorship Program by CAST(2023QNRC001) in part by the National Natural Science Foundation for Young Scientists of China(62001050) in part by the Fundamental Research Funds for the Central Universities(2023RC95) 

主　　题：semantic communication joint source-channel coding image transmission 

摘      要：With the development of deep learning(DL),joint source-channel coding(JSCC)solutions for end-to-end transmission have gained a lot of *** deep JSCC schemes support dynamically adjusting the rate according to different channel conditions during transmission,enhancing robustness in dynamic wireless ***,most of the existing adaptive JSCC schemes only consider different channel conditions,ignoring the different feature importance in the image processing and *** uniform compression of different features in the image may result in the compromise of critical image details,particularly in low signal-to-noise ratio(SNR)*** address the above issues,in this paper,a dual attention mechanism is introduced and an SNR-adaptive deep JSCC mechanism with a convolutional block attention module(CBAM)is proposed,in which matrix operations are applied to features in spatial and channel dimensions *** proposed solution concatenates the pooling feature with the SNR level and passes it sequentially through the channel attention network and spatial attention network to obtain the importance evaluation *** show that the proposed solution outperforms other baseline schemes in terms of peak SNR(PSNR)and structural similarity(SSIM),particularly in low SNR scenarios or when dealing with complex image content.