Side Information Driven Image Coding for Machines

With the continuous improvement of computer vision technology, more and more image information is consumed by machines rather than humans. Image coding for machines (ICM) is to compress image data such that they can be more efficiently sent to the receiver side for machines to conduct visual analysi...

Full description

Saved in:
Bibliographic Details
Published in:Picture Coding Symposium pp. 193 - 197
Main Authors: Zhang, Zhongpeng, Liu, Ying
Format: Conference Proceeding
Language:English
Published: IEEE 07.12.2022
Subjects:
Codecs
hyper-prior
image classification
Image coding
image coding for machines
Internet
Receivers
Semantics
side information
Streaming media
transformer
Visualization
ISSN:2472-7822
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract With the continuous improvement of computer vision technology, more and more image information is consumed by machines rather than humans. Image coding for machines (ICM) is to compress image data such that they can be more efficiently sent to the receiver side for machines to conduct visual analysis. A typical deep learning-based ICM structure contains one codec network which compresses and transmits images through the Internet and one semantic analysis task network such as image classification and object recognition. In the codec part, the side information is the hyper-prior or hierarchical layers of hyper-priors for the compression of image latent representations. In this paper, we propose a Side Information Driven Image Coding (SIIC) framework based on deep learning. It only compresses and transmits the side information to the receiver for image classification tasks. We obtain a top-l accuracy of 70.38% on the ImageNet1K dataset with 0.046 bits per pixel.
AbstractList With the continuous improvement of computer vision technology, more and more image information is consumed by machines rather than humans. Image coding for machines (ICM) is to compress image data such that they can be more efficiently sent to the receiver side for machines to conduct visual analysis. A typical deep learning-based ICM structure contains one codec network which compresses and transmits images through the Internet and one semantic analysis task network such as image classification and object recognition. In the codec part, the side information is the hyper-prior or hierarchical layers of hyper-priors for the compression of image latent representations. In this paper, we propose a Side Information Driven Image Coding (SIIC) framework based on deep learning. It only compresses and transmits the side information to the receiver for image classification tasks. We obtain a top-l accuracy of 70.38% on the ImageNet1K dataset with 0.046 bits per pixel.
Author Zhang, Zhongpeng
Liu, Ying
Author_xml – sequence: 1
  givenname: Zhongpeng
  surname: Zhang
  fullname: Zhang, Zhongpeng
  email: zzhang13@scu.edu
  organization: Santa Clara University,Department of Computer Science and Engineering,Santa Clara,CA,USA,95053
– sequence: 2
  givenname: Ying
  surname: Liu
  fullname: Liu, Ying
  email: yliu15@scu.edu
  organization: Santa Clara University,Department of Computer Science and Engineering,Santa Clara,CA,USA,95053
BookMark eNo1j81KxDAURqMoOI59A5G8QGvuzW-XUh0tjCiMroe0uRkjNpV2EHx7B9TVtziHA985O8ljJsauQFQAor5-bjbaKDQVCsQKhAAnZH3Eito6MEarGrW1x2yBymJpHeIZK-b5XRxMA7rWcsFgkwLxNsdxGvw-jZnfTumLMm8HvyPejCHlHT9Q_uj7t5RpvmCn0X_MVPztkr2u7l6ah3L9dN82N-syoVD70oYoQ-d6C73yBsn7SKSV9cZKcrFHBV10KvShC6q3QfkAEm0EJaPTLsolu_ztJiLafk5p8NP39v-l_AGW0kgP
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/PCS56426.2022.10018039
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
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
Discipline Applied Sciences
EISBN 9781665492577
1665492570
EISSN 2472-7822
EndPage 197
ExternalDocumentID 10018039
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation
  funderid: 10.13039/100000001
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i204t-7df3db8c71c4a62eaafee547a673e8fc241bf84dcdbd4c7d4ad1327f143f858f3
IEDL.DBID RIE
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000926892300032&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:10:43 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i204t-7df3db8c71c4a62eaafee547a673e8fc241bf84dcdbd4c7d4ad1327f143f858f3
PageCount 5
ParticipantIDs ieee_primary_10018039
PublicationCentury 2000
PublicationDate 2022-Dec.-7
PublicationDateYYYYMMDD 2022-12-07
PublicationDate_xml – month: 12
  year: 2022
  text: 2022-Dec.-7
  day: 07
PublicationDecade 2020
PublicationTitle Picture Coding Symposium
PublicationTitleAbbrev PCS
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001615953
Score 1.8443749
Snippet With the continuous improvement of computer vision technology, more and more image information is consumed by machines rather than humans. Image coding for...
SourceID ieee
SourceType Publisher
StartPage 193
SubjectTerms Codecs
hyper-prior
image classification
Image coding
image coding for machines
Internet
Receivers
Semantics
side information
Streaming media
transformer
Visualization
Title Side Information Driven Image Coding for Machines
URI https://ieeexplore.ieee.org/document/10018039
WOSCitedRecordID wos000926892300032&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/eLvHCXMwlV27bsIwFL0qqEMn-qDqWx66BhLb4TozLWqHIiRaiQ35cS0xFCpe31_bhKIOHbpFTiwrJ4rPiXOOL8BjbpQtyUVTu3BZYDyV6YqKzFlExwsTJMSu2AQOh2oyqUZ1WD1lYYgomc-oEw_Tv3y3sJu4VNaN-wWpXFQNaCD2dmGtw4JK4OaqFHUKuMir7qg_LoO8jkYEzjv7zr_KqCQWGbT-Of4ptA95PDb6YZozOKL5ObRqAcnq13N1AcV45ojVCaOIOHtaxtmMvX6GaYP1F7E7C2fZW_JQ0qoNH4Pn9_5LVtdEyGY8l-sMnRcu4IuFlbrHSWtPVErUAWtS3gZCNl5JZ51x0qKT2oXvTfRBFnlVKi8uoTlfzOkKmDYl90GvKSEKyY023lYqXCytRBIKr6EdIZh-7ba9mO7v_uaP9ls4iUAnrwfeQXO93NA9HNvterZaPqSH9Q2SRJQ-
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT8IwHP1F0URP-IHx2x68Dra2s90ZJRCBkIAJN9K1vyYcBMKHf79tKRIPHrwt3Zp0b1nfW_defwDPaSl1jsab2plJHOPJRBWYJUYLYWhWOgmxLTYh-n05HheDGFYPWRhEDOYzrPvD8C_fzPXGL5U1_H5BMmXFIRz50lkxrrVfUnHsXOQs5oCztGgMmsPcCWxvRaC0vuv-q5BK4JFW9Z8jOIPaPpFHBj9ccw4HOLuAapSQJL6gq0vIhlODJGaMPObkdennM9L5dBMHac59d-LOkl5wUeKqBh-tt1GzncSqCMmUpnydCGOZcQiLTHP1QlEpi5hzoRzaKK12lFxayY02peFaGK6M--IU1gkjK3Np2RVUZvMZXgNRZU6tU2ySsYzTUpVWF9JdzDUXyKS4gZqHYLLYbnwx2d397R_tT3DSHvW6k26n_34Hpx704PwQ91BZLzf4AMf6az1dLR_Dg_sGfxyXhw
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=Picture+Coding+Symposium&rft.atitle=Side+Information+Driven+Image+Coding+for+Machines&rft.au=Zhang%2C+Zhongpeng&rft.au=Liu%2C+Ying&rft.date=2022-12-07&rft.pub=IEEE&rft.eissn=2472-7822&rft.spage=193&rft.epage=197&rft_id=info:doi/10.1109%2FPCS56426.2022.10018039&rft.externalDocID=10018039