Device Interoperability for Learned Image Compression with Weights and Activations Quantization

Learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance. In addition to good compression performance, device interoperability is essential for a compression codec to be deployed, i.e., encoding and...

Full description

Saved in:
Bibliographic Details
Published in:Picture Coding Symposium pp. 151 - 155
Main Authors: Koyuncu, Esin, Solovyev, Timofey, Alshina, Elena, Kaup, Andre
Format: Conference Proceeding
Language:English
Published: IEEE 07.12.2022
Subjects:
Codecs
Decoding
device interoperability
Entropy
Image coding
Interoperability
learning-based image compression
neural network quantization
Performance evaluation
Quantization (signal)
ISSN:2472-7822
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance. In addition to good compression performance, device interoperability is essential for a compression codec to be deployed, i.e., encoding and decoding on different CPUs or GPUs should be error-free and with negligible performance reduction. In this paper, we present a method to solve the device interoperability problem of a state-of-the-art image compression network. We implement quantization to entropy networks which output entropy parameters. We suggest a simple method which can ensure cross-platform encoding and decoding, and can be implemented quickly with minor performance deviation, of 0.3% BD-rate, from floating point model results.
AbstractList Learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance. In addition to good compression performance, device interoperability is essential for a compression codec to be deployed, i.e., encoding and decoding on different CPUs or GPUs should be error-free and with negligible performance reduction. In this paper, we present a method to solve the device interoperability problem of a state-of-the-art image compression network. We implement quantization to entropy networks which output entropy parameters. We suggest a simple method which can ensure cross-platform encoding and decoding, and can be implemented quickly with minor performance deviation, of 0.3% BD-rate, from floating point model results.
Author Alshina, Elena
Koyuncu, Esin
Kaup, Andre
Solovyev, Timofey
Author_xml – sequence: 1
  givenname: Esin
  surname: Koyuncu
  fullname: Koyuncu, Esin
  email: andre.kaup@fau.de
  organization: Multimedia Communications and Signal Processing Friedrich-Alexander-Universität Erlangen-Nüurnberg,Erlangen,Germany
– sequence: 2
  givenname: Timofey
  surname: Solovyev
  fullname: Solovyev, Timofey
  email: esin.koyuncu@fau.de
  organization: Audiovisual Laboratory, Munich Research Center Huawei Technologies,Munich,Germany
– sequence: 3
  givenname: Elena
  surname: Alshina
  fullname: Alshina, Elena
  email: elena.alshina@huawei.com
  organization: Audiovisual Laboratory, Munich Research Center Huawei Technologies,Munich,Germany
– sequence: 4
  givenname: Andre
  surname: Kaup
  fullname: Kaup, Andre
  email: solovyev.timofey@huawei.com
  organization: Multimedia Communications and Signal Processing Friedrich-Alexander-Universität Erlangen-Nüurnberg,Erlangen,Germany
BookMark eNo1kNtKAzEYhKMoWGvfQCQvsDX5N4fdy7JaLRRULHhZsps_baTNliRW6tNbPMzNMHzDXMwlOQt9QEJuOBtzzurb5-ZVKgFqDAxgzBnjFRPshIxqXXGlpKhBan1KBiA0FLoCuCCjlN7Zsam4rGU5IMs73PsO6SxkjP0Oo2n9xucDdX2kczQxoKWzrVkhbfrtLmJKvg_00-c1fUO_WudETbB00mW_N_nIEn35MCH7r590Rc6d2SQc_fmQLKb3i-axmD89zJrJvPDARC6kRatV3VZStvIoFJ1CXjthLDgHbSfQoHIllwJLiZ3jYLkGa6uSqa4sh-T6d9Yj4nIX_dbEw_L_kvIbnahZYg
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/PCS56426.2022.10018040
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 155
ExternalDocumentID 10018040
Genre orig-research
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-5ded769b855b5555e4c6e19f4ad2ff2bc4eae6f3154e35ecf12d172dd8306c33
IEDL.DBID RIE
ISICitedReferencesCount 8
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000926892300025&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-5ded769b855b5555e4c6e19f4ad2ff2bc4eae6f3154e35ecf12d172dd8306c33
PageCount 5
ParticipantIDs ieee_primary_10018040
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 1.9092625
Snippet Learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance....
SourceID ieee
SourceType Publisher
StartPage 151
SubjectTerms Codecs
Decoding
device interoperability
Entropy
Image coding
Interoperability
learning-based image compression
neural network quantization
Performance evaluation
Quantization (signal)
Title Device Interoperability for Learned Image Compression with Weights and Activations Quantization
URI https://ieeexplore.ieee.org/document/10018040
WOSCitedRecordID wos000926892300025&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/eLvHCXMwlV1LS8NAEB5s8eCpPiq-2YPXbZvHPnKUqihIqViwt7LZnUAPpqVpBf-9s5vU4sGDOYWQEJh9zDffzjcDcCutpmkhBtxzbDy1KLkh2MCTTDo0ca60CSXzX9RopKfTbNyI1YMWBhFD8hn2_G04y3cLu_FUWd_XC9I061rQUkrWYq0doUK-ORNJowKOBll_PHwTBK99IkIc97Yf_2qjErzIY-ef_z-E7k6Px8Y_nuYI9rA8hk4DIFmzPKsTmN2jX_gs0HyLJa7qItxfjJApC5VU6fXnD9pCmN8H6hTYknkulr0HjrRipnTszm6bnlXsdUO2b8SaXZg8PkyGT7zpoMDn8SBdc-HQKZnlWohc0IWplRhlRWpcXBRxblM0KIuEcBQmAm0RxY4QjXOaIgmbJKfQLhclngFzkc1TRcEHal_TjUCJsc4JQTFu7iKjzqHr7TVb1jUyZltTXfzx_BIO_KiExBB1Be31aoPXsG8_1_NqdRNG9htRgqV_
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF60Cnqqj4pv9-A1bbLZTTZHqZYWa6lYsLew2Z1AD6alaQX_vbOb1OLBgzmFkECYfcw33843Q8h9pCVOC-F7lmPzuIbIUwgbvDCJDCiWxVK5kvnDeDSS02kyrsXqTgsDAC75DNr21p3lm7leW6qsY-sFSZx1u2RPcM78Sq61pVTQOycirHXAgZ90xt03gQDbpiIw1t58_quRivMjveY__-CItLaKPDr-8TXHZAeKE9KsISStF2h5StJHsEufOqJvvoBlVYb7iyI2pa6WKr4--MBNhNqdoEqCLahlY-m7Y0lLqgpDH_Sm7VlJX9do_Vqu2SKT3tOk2_fqHgrejPl85QkDJo6STAqRCbyA6wiCJOfKsDxnmeagIMpDRFIQCtB5wAxiGmMkxhI6DM9Io5gXcE6oCXTGYww_QNqqbghLlDZGCIxyMxOo-IK0rL3SRVUlI92Y6vKP53fkoD95GabDwej5ihzaEXJpIvE1aayWa7gh-_pzNSuXt26UvwEZ1ajG
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=Device+Interoperability+for+Learned+Image+Compression+with+Weights+and+Activations+Quantization&rft.au=Koyuncu%2C+Esin&rft.au=Solovyev%2C+Timofey&rft.au=Alshina%2C+Elena&rft.au=Kaup%2C+Andre&rft.date=2022-12-07&rft.pub=IEEE&rft.eissn=2472-7822&rft.spage=151&rft.epage=155&rft_id=info:doi/10.1109%2FPCS56426.2022.10018040&rft.externalDocID=10018040