Adaptive Information Bottleneck Guided Joint Source and Channel Coding for Image Transmission

被引:18
作者
Sun, Lunan [1 ]
Yang, Yang [1 ]
Chen, Mingzhe [2 ,3 ]
Guo, Caili [4 ]
Saad, Walid [5 ]
Poor, H. Vincent [6 ]
机构
[1] Beijing Univ Posts & Telecommun, Sch Informat & Commun Engn, Beijing Key Lab Network Syst Architecture & Conver, Beijing 100876, Peoples R China
[2] Univ Miami, Dept Elect & Comp Engn, Coral Gables, FL 33146 USA
[3] Univ Miami, Inst Data Sci & Comp, Coral Gables, FL 33146 USA
[4] Beijing Univ Posts & Telecommun, Sch Informat & Commun Engn, Beijing Lab Adv Informat Net works, Beijing 100876, Peoples R China
[5] Virginia Tech, Bradley Dept Elect & Comp Engn, Wireless VT Grp, Arlington, VA 24061 USA
[6] Princeton Univ, Dept Elect & Comp Engn, Princeton, NJ 08544 USA
基金
中国国家自然科学基金; 美国国家科学基金会; 北京市自然科学基金;
关键词
Information bottleneck; joint source and channel coding; image transmission; CHECK; BLOCK;
D O I
10.1109/JSAC.2023.3288238
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Joint source and channel coding (JSCC) for image transmission has attracted increasing attention due to its robustness and high efficiency. However, the existing deep JSCC research mainly focuses on minimizing the distortion between the transmitted and received information under a fixed number of available channels. Therefore, the transmitted rate may be far more than its required minimum value. In this paper, an adaptive information bottleneck (IB) guided joint source and channel coding (AIB-JSCC) method is proposed for image transmission. The goal of AIB-JSCC is to reduce the transmission rate while improving the image reconstruction quality. In particular, a new IB objective for image transmission is proposed so as to minimize the distortion and the transmission rate. A mathematically tractable lower bound on the proposed objective is derived, and then, adopted as the loss function of AIB-JSCC. To trade off compression and reconstruction quality, an adaptive algorithm is proposed to adjust the hyperparameter of the proposed loss function dynamically according to the distortion during the training. Experimental results show that AIB-JSCC can significantly reduce the required amount of transmitted data and improve the reconstruction quality and downstream task accuracy.
引用
收藏
页码:2628 / 2644
页数:17
相关论文
共 55 条
[1]  
Alemi AA, 2019, Arxiv, DOI arXiv:1612.00410
[2]  
[Anonymous], Technical report
[3]  
[Anonymous], 2020, PMLR
[4]  
Barber D, 2004, ADV NEUR IN, V16, P201
[5]  
Bellard Fabrice, 2018, BPG Image Format
[6]   INHERENT INTRACTABILITY OF CERTAIN CODING PROBLEMS [J].
BERLEKAMP, ER ;
MCELIECE, RJ ;
VANTILBORG, HCA .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1978, 24 (03) :384-386
[7]   Large-Scale Machine Learning with Stochastic Gradient Descent [J].
Bottou, Leon .
COMPSTAT'2010: 19TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL STATISTICS, 2010, :177-186
[8]   Directional Terahertz Communication Systems for 6G: Fact Check: A Quantitative Look [J].
Boulogeorgos, Alexandros-Apostolos A. ;
Jornet, Josep Miguel ;
Alexiou, Angeliki .
IEEE VEHICULAR TECHNOLOGY MAGAZINE, 2021, 16 (04) :68-77
[9]   Deep Joint Source-Channel Coding for Wireless Image Transmission [J].
Bourtsoulatze, Eirina ;
Kurka, David Burth ;
Gunduz, Deniz .
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2019, 5 (03) :567-579
[10]  
Chafii M, 2022, Arxiv, DOI arXiv:2207.01843