Distributed Deep Joint Source-Channel Coding with Decoder-Only Side Information

We consider low-latency image transmission over a noisy wireless channel when correlated side information is present only at the receiver side (the Wyner-Ziv scenario). In particular, we are interested in developing practical schemes using a data-driven joint source-channel coding (JSCC) approach, w...

Full description

Saved in:
Bibliographic Details
Published in:2024 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN) pp. 139 - 144
Main Authors: Yilmaz, Selim F., Ozyilkan, Ezgi, Gunduz, Deniz, Erkip, Elza
Format: Conference Proceeding
Language:English
Published: IEEE 05.05.2024
Subjects:
deep learning
Image communication
Joint source-channel coding
multi-view learning
Receivers
Robustness
Source coding
Time-varying channels
Wireless communication
wireless image transmission
Wireless sensor networks
Wyner-Ziv coding
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract We consider low-latency image transmission over a noisy wireless channel when correlated side information is present only at the receiver side (the Wyner-Ziv scenario). In particular, we are interested in developing practical schemes using a data-driven joint source-channel coding (JSCC) approach, which has been previously shown to outperform conventional separation-based approaches in the practical finite blocklength regimes, and to provide graceful degradation with channel quality. We propose a novel neural network architecture that incorporates the decoder-only side information at multiple stages at the receiver side. Our results demonstrate that the proposed method succeeds in integrating the side information, yielding improved performance at all channel conditions in terms of the various quality measures considered here, especially at low channel signal-to-noise ratios (SNRs) and small bandwidth ratios (BRs). We have made the source code of the proposed method public to enable further research, and the reproducibility of the results.
AbstractList We consider low-latency image transmission over a noisy wireless channel when correlated side information is present only at the receiver side (the Wyner-Ziv scenario). In particular, we are interested in developing practical schemes using a data-driven joint source-channel coding (JSCC) approach, which has been previously shown to outperform conventional separation-based approaches in the practical finite blocklength regimes, and to provide graceful degradation with channel quality. We propose a novel neural network architecture that incorporates the decoder-only side information at multiple stages at the receiver side. Our results demonstrate that the proposed method succeeds in integrating the side information, yielding improved performance at all channel conditions in terms of the various quality measures considered here, especially at low channel signal-to-noise ratios (SNRs) and small bandwidth ratios (BRs). We have made the source code of the proposed method public to enable further research, and the reproducibility of the results.
Author Gunduz, Deniz
Yilmaz, Selim F.
Erkip, Elza
Ozyilkan, Ezgi
Author_xml – sequence: 1
  givenname: Selim F.
  surname: Yilmaz
  fullname: Yilmaz, Selim F.
  email: s.yilmaz21@imperial.ac.uk
  organization: Imperial College,Department of Electrical and Electronic Engineering,London,UK
– sequence: 2
  givenname: Ezgi
  surname: Ozyilkan
  fullname: Ozyilkan, Ezgi
  email: ezgi.ozyilkan@nyu.edu
  organization: New York University,Department of Electrical and Computer Engineering,USA
– sequence: 3
  givenname: Deniz
  surname: Gunduz
  fullname: Gunduz, Deniz
  email: d.gunduz@imperial.ac.uk
  organization: Imperial College,Department of Electrical and Electronic Engineering,London,UK
– sequence: 4
  givenname: Elza
  surname: Erkip
  fullname: Erkip, Elza
  email: elza@nyu.edu
  organization: New York University,Department of Electrical and Computer Engineering,USA
BookMark eNo1j71OwzAYAI0EA5S-AYN5gITPdmzHI3L5CQpkKMyVE3-mllK7SlOhvj1IwHTL6aS7IucpJyTklkHJGJi7xr629k0aqE3JgVclA8UlZ9UZWRptaiFBVIIZc0m6VTzMU-yPM3q6QtzTlxzTTNf5OA1Y2K1LCUdqs4_pk37FeftjDdnjVHRpPNF19EibFPK0c3PM6ZpcBDcecPnHBfl4fHi3z0XbPTX2vi0i02oucAAuA-e6h571A-rgRMWdBnABHXgpA2iUXnkYuPBKehN6Z2qjnEamgliQm99uRMTNfoo7N502_5_iGxWjTnc
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICMLCN59089.2024.10625214
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350343199
EndPage 144
ExternalDocumentID 10625214
Genre orig-research
GrantInformation_xml – fundername: CHIST-ERA
  funderid: 10.13039/501100001942
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i176t-ec025f227b0b1bce7fa342a700afea0d55f07e5d6d0c23d65d9fba9896a7e16f3
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001307813600025&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu May 29 05:57:37 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i176t-ec025f227b0b1bce7fa342a700afea0d55f07e5d6d0c23d65d9fba9896a7e16f3
PageCount 6
ParticipantIDs ieee_primary_10625214
PublicationCentury 2000
PublicationDate 2024-May-5
PublicationDateYYYYMMDD 2024-05-05
PublicationDate_xml – month: 05
  year: 2024
  text: 2024-May-5
  day: 05
PublicationDecade 2020
PublicationTitle 2024 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN)
PublicationTitleAbbrev ICMLCN
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.9264351
Snippet We consider low-latency image transmission over a noisy wireless channel when correlated side information is present only at the receiver side (the Wyner-Ziv...
SourceID ieee
SourceType Publisher
StartPage 139
SubjectTerms deep learning
Image communication
Joint source-channel coding
multi-view learning
Receivers
Robustness
Source coding
Time-varying channels
Wireless communication
wireless image transmission
Wireless sensor networks
Wyner-Ziv coding
Title Distributed Deep Joint Source-Channel Coding with Decoder-Only Side Information
URI https://ieeexplore.ieee.org/document/10625214
WOSCitedRecordID wos001307813600025&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwEA46RHxSceJvIviamaZN0j53DhXdBlPY20ibCxRGO7ZO8L-3l3WKDz74FsKFwB3hji_33UfInQp1U6bGERN5EHi0iiXaxMyBMlaqTAizEZvQw2E8nSbjlqzuuTAA4JvPoIdL_5dvq3yNUFnzwptqXaBs9a7WakPW2ie37dzM-6f09SUdoog3MlBE1Nva_1JO8YljcPjPK49I94eCR8ffyeWY7EB5QkZ9HHOLClVgaR9gQZ-roqzpxCPwDJkCJcxpWuEZihBrY4Wk9SUblfNPOiks0JaAhAHpkvfBw1v6yFpFBFYEWtUM8qZEcULojGdBloN2JoyE0ZwbB4ZbKR3XIK2yPBehVdImLjNJnCijIVAuPCWdsirhjFActKdjlUmZ2yhyypgmUwcceOywrInPSRe9MVtshl7Mto64-GP_khygz30voLwinXq5hmuyl3_UxWp540P1BZu8lXo
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwEA4yRX1SceJvI_iamaZN0j53jk23brAJextpc4HCaMfsBP97m6wqPvjgWwg5AneEO77cdx9CD8KXdZkaBoRlnufQKhJJFRIDQmkuUsbUVmxCJkk4n0eThqzuuDAA4JrPoGOX7i9fl9nGQmX1C6-rdWZlq3d5EDC6pWvto_tmcubjIB4N48TKeFsOCgs6Xxa_tFNc6ugd_fPSY9T-IeHhyXd6OUE7UJyicdcOurUaVaBxF2CFn8u8qPDUYfDEcgUKWOK4tDbYgqz1KUtbX5NxsfzA01wDbihINiRt9Np7msV90mgikNyToiKQ1UWKYUymNPXSDKRRfsCUpFQZUFRzbqgEroWmGfO14DoyqYrCSCgJnjD-GWoVZQHnCNtRezIUKeeZDgIjlKpztUeBhsYWNuEFaltvLFbbsReLL0dc_rF_hw76s9FwMRwkL1fo0PrfdQbya9Sq1hu4QXvZe5W_rW9d2D4BkfOYwQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2024+IEEE+International+Conference+on+Machine+Learning+for+Communication+and+Networking+%28ICMLCN%29&rft.atitle=Distributed+Deep+Joint+Source-Channel+Coding+with+Decoder-Only+Side+Information&rft.au=Yilmaz%2C+Selim+F.&rft.au=Ozyilkan%2C+Ezgi&rft.au=Gunduz%2C+Deniz&rft.au=Erkip%2C+Elza&rft.date=2024-05-05&rft.pub=IEEE&rft.spage=139&rft.epage=144&rft_id=info:doi/10.1109%2FICMLCN59089.2024.10625214&rft.externalDocID=10625214