Demo: Real-Time Semantic Communications with a Vision Transformer

Hanju Yoo; Taehun Jung; Linglong Dai; Songkuk Kim; Chan Byoung Chae

doi:10.1109/ICCWorkshops53468.2022.9914635

Demo: Real-Time Semantic Communications with a Vision Transformer

Hanju Yoo, Taehun Jung, Linglong Dai, Songkuk Kim, Chan Byoung Chae

School of Integrated Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

21 Citations (Scopus)

Abstract

Semantic communications are expected to enable the more effective delivery of meaning rather than a precise transfer of symbols. In this paper, we propose an end-To-end deep neural network-based architecture for image transmission and demonstrate its feasibility in a real-Time wireless channel by implementing a prototype based on a field-programmable gate array (FPGA). We demonstrate that this system outperforms the traditional 256-quadrature amplitude modulation system in the low signal-To-noise ratio regime with the popular CIFAR-10 dataset. To the best of our knowledge, this is the first work that implements and investigates real-Time semantic communications with a vision transformer.

Original language	English
Title of host publication	2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665426718
DOIs	https://doi.org/10.1109/ICCWorkshops53468.2022.9914635
Publication status	Published - 2022
Event	2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022 - Seoul, Korea, Republic of Duration: 2022 May 16 → 2022 May 20

Publication series

Name	2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022
Volume	2022-January

Conference

Conference	2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022
Country/Territory	Korea, Republic of
City	Seoul
Period	22/5/16 → 22/5/20

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Networks and Communications
Signal Processing
Control and Optimization

Access to Document

10.1109/ICCWorkshops53468.2022.9914635

Cite this

Yoo, H., Jung, T., Dai, L., Kim, S., & Chae, C. B. (2022). Demo: Real-Time Semantic Communications with a Vision Transformer. In 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022 (2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022; Vol. 2022-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCWorkshops53468.2022.9914635

@inproceedings{816d35553e1841e78f5f79d72a1cd77f,

title = "Demo: Real-Time Semantic Communications with a Vision Transformer",

abstract = "Semantic communications are expected to enable the more effective delivery of meaning rather than a precise transfer of symbols. In this paper, we propose an end-To-end deep neural network-based architecture for image transmission and demonstrate its feasibility in a real-Time wireless channel by implementing a prototype based on a field-programmable gate array (FPGA). We demonstrate that this system outperforms the traditional 256-quadrature amplitude modulation system in the low signal-To-noise ratio regime with the popular CIFAR-10 dataset. To the best of our knowledge, this is the first work that implements and investigates real-Time semantic communications with a vision transformer.",

keywords = "Semantic communications, deep neural network, image transmission, real-Time wireless communications",

author = "Hanju Yoo and Taehun Jung and Linglong Dai and Songkuk Kim and Chae, {Chan Byoung}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022 ; Conference date: 16-05-2022 Through 20-05-2022",

year = "2022",

doi = "10.1109/ICCWorkshops53468.2022.9914635",

language = "English",

series = "2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022",

address = "United States",

}

Yoo, H, Jung, T, Dai, L, Kim, S & Chae, CB 2022, Demo: Real-Time Semantic Communications with a Vision Transformer. in 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022. 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022, vol. 2022-January, Institute of Electrical and Electronics Engineers Inc., 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022, Seoul, Korea, Republic of, 22/5/16. https://doi.org/10.1109/ICCWorkshops53468.2022.9914635

Demo: Real-Time Semantic Communications with a Vision Transformer. / Yoo, Hanju; Jung, Taehun; Dai, Linglong et al.
2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022; Vol. 2022-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Demo

T2 - 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022

AU - Yoo, Hanju

AU - Jung, Taehun

AU - Dai, Linglong

AU - Kim, Songkuk

AU - Chae, Chan Byoung

PY - 2022

Y1 - 2022

N2 - Semantic communications are expected to enable the more effective delivery of meaning rather than a precise transfer of symbols. In this paper, we propose an end-To-end deep neural network-based architecture for image transmission and demonstrate its feasibility in a real-Time wireless channel by implementing a prototype based on a field-programmable gate array (FPGA). We demonstrate that this system outperforms the traditional 256-quadrature amplitude modulation system in the low signal-To-noise ratio regime with the popular CIFAR-10 dataset. To the best of our knowledge, this is the first work that implements and investigates real-Time semantic communications with a vision transformer.

AB - Semantic communications are expected to enable the more effective delivery of meaning rather than a precise transfer of symbols. In this paper, we propose an end-To-end deep neural network-based architecture for image transmission and demonstrate its feasibility in a real-Time wireless channel by implementing a prototype based on a field-programmable gate array (FPGA). We demonstrate that this system outperforms the traditional 256-quadrature amplitude modulation system in the low signal-To-noise ratio regime with the popular CIFAR-10 dataset. To the best of our knowledge, this is the first work that implements and investigates real-Time semantic communications with a vision transformer.

KW - Semantic communications

KW - deep neural network

KW - image transmission

KW - real-Time wireless communications

UR - http://www.scopus.com/inward/record.url?scp=85141221298&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85141221298&partnerID=8YFLogxK

U2 - 10.1109/ICCWorkshops53468.2022.9914635

DO - 10.1109/ICCWorkshops53468.2022.9914635

M3 - Conference contribution

AN - SCOPUS:85141221298

T3 - 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022

BT - 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 16 May 2022 through 20 May 2022

ER -

Yoo H, Jung T, Dai L, Kim S , Chae CB. Demo: Real-Time Semantic Communications with a Vision Transformer. In 2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022). doi: 10.1109/ICCWorkshops53468.2022.9914635

Demo: Real-Time Semantic Communications with a Vision Transformer

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this