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

doi:10.19682/j.cnki.1005-8885.2024.2001

中国邮电高校学报(英文) ›› 2024, Vol. 31 ›› Issue (1): 1-11.doi: 10.19682/j.cnki.1005-8885.2024.2001

• • 下一篇

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

Yang Yujia, Liu Yiming, Zhang Wenjia, Zhang Zhi

State Key Laboratory of Networking and Switch Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China

收稿日期:2023-11-21 修回日期:2024-01-04 接受日期:2024-02-22 出版日期:2024-02-29 发布日期:2024-02-29
通讯作者: Corresponding author: Liu Yiming, E-mail: liuyiming@bupt.edu.cn E-mail:liuyiming@bupt.edu.cn
基金资助:
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), and in part by the Fundamental Research Funds for the Central Universities (2023RC95).

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

Yang Yujia, Liu Yiming, Zhang Wenjia, Zhang Zhi

State Key Laboratory of Networking and Switch Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2023-11-21 Revised:2024-01-04 Accepted:2024-02-22 Online:2024-02-29 Published:2024-02-29
Contact: Corresponding author: Liu Yiming, E-mail: liuyiming@bupt.edu.cn E-mail:liuyiming@bupt.edu.cn
Supported by:
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), and in part by the Fundamental Research Funds for the Central Universities (2023RC95).

摘要/Abstract

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 attention. Adaptive deep JSCC schemes support dynamically adjusting the rate according to different channel conditions during transmission, enhancing robustness in dynamic wireless environment. However, most of the existing adaptive JSCC schemes only consider different channel conditions, ignoring the different feature importance in the image processing and transmission. The 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) scenarios. To 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 respectively. The proposedsolution 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 result. Experiments 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.

关键词: semantic communication, joint source-channel coding, image transmission

Abstract: With the development of deep learning (DL), joint source-channel coding (JSCC) solutions for end-to-end transmission have gained a lot of attention. Adaptive deep JSCC schemes support dynamically adjusting the rate according to different channel conditions during transmission, enhancing robustness in dynamic wireless environment. However, most of the existing adaptive JSCC schemes only consider different channel conditions, ignoring the different feature importance in the image processing and transmission. The 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) scenarios. To 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 respectively. The proposedsolution 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 result. Experiments 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.

Key words: semantic communication, joint source-channel coding, image transmission

Yang Yujia, Liu Yiming, Zhang Wenjia, Zhang Zhi. SNR-adaptive deep joint source-channel coding scheme for imagesemantic transmission with convolutional block attention module[J]. The Journal of China Universities of Posts and Telecommunications, 2024, 31(1): 1-11.

参考文献

References

[1] BOURTSOULATZE E, KURKA D B, GUNDUZ D. Deep joint source-channel coding for wireless image transmission. IEEE Transactions on Cognitive Communications and Networking, 2019, 5(3): 567 - 579.

[2] KURKA D B, GUNDUZ D. Successive refinement of images withdeep joint source-channel coding. Proceedings of the IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC'19), 2019, Jul 2 - 5, Cannes, France. Piscataway, NJ, USA: IEEE, 2019: 1 - 5.

[3] YANG M Y, KIM H S. Deep joint source-channel coding for wireless image transmission with adaptive rate control. Proceedings of the 2022 IEEE International Conference on Acoustics, Speechand Signal Processing (ICASSP'22), 2022, May 23 - 27, Singapore. Piscataway, NJ, USA: IEEE, 2022: 5193 - 5197.

[4] KURKA D B, GUNDUZ D. Deep joint source-channel coding of images with feedback. Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'20), 2020, May 4 - 8, Barcelona, Spain. Piscataway, NJ, USA: IEEE, 2020: 5235 - 5239.

[5] ZHANG Z G, YANG Q Q, HE S B, et al. Semantic communication approach for multi-task image transmission. Proceedings of the IEEE 96th Vehicular Technology Conference (VTC-Fall'22), 2022, Sept 26 - 29, London, UK. Piscataway, NJ, USA: IEEE, 2022: 1 - 2.[6] KANG J W, DU H Y, LI Z H, et al. Personalized saliency in task-oriented semantic communications: Image transmission and performance analysis. IEEE Journal on Selected Areas in Communications, 2023, 41(1): 186 - 201.

[7] XU J L, AI B, CHEN W, et al. Wireless image transmission using deep source channel coding with attention modules. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(4): 2315 - 2328.

[8] BAO X W, JIANG M, ZHANG H. ADJSCC-l: SNR-adaptive JSCC networks for multi-layer wireless image transmission. Proceedings of the 7th International Conference on Computer and Communications (ICCC'21), 2021, Dec 10 - 13, Chengdu, China. Piscataway, NJ, USA: IEEE, 2021: 1812 - 1816.

[9] BALLE J, LAPARRA V, SIMONCELLI E P. Density modeling of images using a generalized normalization transformation. arXiv Preprint, arXiv: 1511. 06281, 2016.

[10] HE K M, ZHANG X Y, REN S Q, et al. Delving deep intorectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV'15), 2015, Dec 7 - 13, Santiago, Chile. Piscataway, NJ, USA: IEEE, 2015: 1026 -1034.

[11] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'16), 2016, Jun 27 - 30, Las Vegas, NV, USA. Piscataway, NJ, USA: IEEE, 2016: 770 - 778.

[12] HE K M, ZHANG X Y, REN S Q, et al. Identity mappings in deep residual networks. Computer Vision: Proceedings of the 14th European Conference on Computer Vision (ECCV'16), 2016, Oct 11 - 14, Amsterdam, Netherlands. LNIP 9908. Berlin, Germany: Springer, 2016: 630 - 645.

[13] KRIZHEVSKY A. Learning multiple layers of features from tiny images. Corpus ID:18268744. Toronto, Canada: University of Toronto, 2009. https://www. cs. toronto. edu/~ kriz/learning-features-2009-TR. pdf.

[14] ABADI M, AGARWAL A, BARHAM P, et al. TensorFlow: Large-scale machine learning on heterogeneous distributed systems. arXiv Preprint, arXiv: 1603. 04467, 2016.

[15] KINGMA D P, BA J. Adam: A method for stochastic optimization. arXiv Preprint, arXiv: 1412. 6980, 2014.

[16] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 2004, 13(4): 600 - 612.

[17] KURKA D B, GUNDUZ D. DeepJSCC-f: Deep joint source-channel coding of images with feedback. IEEE Journal on Selected Areas in Information Theory, 2020, 1(1): 178 - 193.

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

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

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价