Nonlinear Transform Coding

We review a class of methods that can be collected under the name nonlinear transform coding (NTC), which over the past few years have become competitive with the best linear transform codecs for images, and have superseded them in terms of rate-distortion performance under established perceptual qu...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE journal of selected topics in signal processing Ročník 15; číslo 2; s. 339 - 353
Hlavní autoři: Balle, Jona, Chou, Philip A., Minnen, David, Singh, Saurabh, Johnston, Nick, Agustsson, Eirikur, Hwang, Sung Jin, Toderici, George
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.02.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:1932-4553, 1941-0484
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We review a class of methods that can be collected under the name nonlinear transform coding (NTC), which over the past few years have become competitive with the best linear transform codecs for images, and have superseded them in terms of rate-distortion performance under established perceptual quality metrics such as MS-SSIM. We assess the empirical rate-distortion performance of NTC with the help of simple example sources, for which the optimal performance of a vector quantizer is easier to estimate than with natural data sources. To this end, we introduce a novel variant of entropy-constrained vector quantization. We provide an analysis of various forms of stochastic optimization techniques for NTC models; review architectures of transforms based on artificial neural networks, as well as learned entropy models; and provide a direct comparison of a number of methods to parameterize the rate-distortion trade-off of nonlinear transforms, introducing a simplified one.
AbstractList We review a class of methods that can be collected under the name nonlinear transform coding (NTC), which over the past few years have become competitive with the best linear transform codecs for images, and have superseded them in terms of rate–distortion performance under established perceptual quality metrics such as MS-SSIM. We assess the empirical rate–distortion performance of NTC with the help of simple example sources, for which the optimal performance of a vector quantizer is easier to estimate than with natural data sources. To this end, we introduce a novel variant of entropy-constrained vector quantization. We provide an analysis of various forms of stochastic optimization techniques for NTC models; review architectures of transforms based on artificial neural networks, as well as learned entropy models; and provide a direct comparison of a number of methods to parameterize the rate–distortion trade-off of nonlinear transforms, introducing a simplified one.
Author Toderici, George
Singh, Saurabh
Agustsson, Eirikur
Minnen, David
Chou, Philip A.
Balle, Jona
Johnston, Nick
Hwang, Sung Jin
Author_xml – sequence: 1
  givenname: Jona
  orcidid: 0000-0003-0769-8985
  surname: Balle
  fullname: Balle, Jona
  email: jballe@google.com
  organization: Google Research, Mountain View, CA, USA
– sequence: 2
  givenname: Philip A.
  orcidid: 0000-0002-7242-0210
  surname: Chou
  fullname: Chou, Philip A.
  email: philchou@google.com
  organization: Google Research, Mountain View, CA, USA
– sequence: 3
  givenname: David
  surname: Minnen
  fullname: Minnen, David
  email: dminnen@google.com
  organization: Google Research, Mountain View, CA, USA
– sequence: 4
  givenname: Saurabh
  surname: Singh
  fullname: Singh, Saurabh
  email: saurabhsingh@google.com
  organization: Google Research, Mountain View, CA, USA
– sequence: 5
  givenname: Nick
  surname: Johnston
  fullname: Johnston, Nick
  email: nickj@google.com
  organization: Google Research, Mountain View, CA, USA
– sequence: 6
  givenname: Eirikur
  surname: Agustsson
  fullname: Agustsson, Eirikur
  email: eirikur@google.com
  organization: Google Research, Mountain View, CA, USA
– sequence: 7
  givenname: Sung Jin
  surname: Hwang
  fullname: Hwang, Sung Jin
  email: sjhwang@google.com
  organization: Google Research, Mountain View, CA, USA
– sequence: 8
  givenname: George
  surname: Toderici
  fullname: Toderici, George
  email: gtoderici@google.com
  organization: Google Research, Mountain View, CA, USA
BookMark eNp9kMFOAjEURRuDiYD-AG5IXA-2fW8606UhihqiJuC6aWdaUwIttsPCvxeEuHDh6r7FPe8mZ0B6IQZLyIjRCWNU3j4vlou3CaecToAClpSdkT6TyAqKNfYON_ACyxIuyCDnFaVlJRj2yeglhrUPVqfxMumQXUyb8TS2PnxcknOn19lenXJI3h_ul9PHYv46e5rezYsGQHaFttZUtAUQtnZClKYWlXEIxtVGIvDWOMcAmaMVUsbatq4abqTTzFgpQMOQ3Bz_blP83NncqVXcpbCfVBwlCIolwr5VH1tNijkn61TjO935GLqk_Voxqg4m1I8JdTChTib2KP-DbpPf6PT1P3R9hLy19heQHDnHCr4B5v9qUA
CODEN IJSTGY
CitedBy_id crossref_primary_10_1109_JIOT_2023_3293154
crossref_primary_10_1109_TMM_2022_3187259
crossref_primary_10_1186_s13634_022_00958_0
crossref_primary_10_1109_JSAC_2025_3559128
crossref_primary_10_1016_j_engappai_2025_111439
crossref_primary_10_1109_JSTSP_2023_3304140
crossref_primary_10_1109_JSAC_2022_3180802
crossref_primary_10_1109_TVCG_2022_3209419
crossref_primary_10_1109_JSAC_2025_3559120
crossref_primary_10_1145_3592407
crossref_primary_10_1109_JSTSP_2024_3482972
crossref_primary_10_1109_LGRS_2023_3325477
crossref_primary_10_1186_s13640_024_00652_1
crossref_primary_10_1109_MBITS_2023_3339111
crossref_primary_10_1016_j_eng_2025_08_039
crossref_primary_10_1016_j_sigpro_2023_109128
crossref_primary_10_1109_ACCESS_2025_3597217
crossref_primary_10_1109_JSAC_2023_3288246
crossref_primary_10_1145_3730879
crossref_primary_10_1109_TGCN_2023_3275199
crossref_primary_10_1109_TMC_2025_3544516
crossref_primary_10_1016_j_isprsjprs_2024_12_016
crossref_primary_10_1016_j_sigpro_2024_109741
crossref_primary_10_3390_rs15184422
crossref_primary_10_1007_s11263_023_01809_7
crossref_primary_10_1109_JSAC_2025_3559158
crossref_primary_10_1016_j_jvcir_2024_104294
crossref_primary_10_1109_JSTARS_2024_3422215
crossref_primary_10_1145_3719011
crossref_primary_10_1109_JSAC_2025_3559156
crossref_primary_10_1109_TIT_2023_3247601
crossref_primary_10_1109_LSP_2023_3279780
crossref_primary_10_1007_s11042_022_12216_4
crossref_primary_10_1109_TCSVT_2023_3300316
crossref_primary_10_1109_JSAC_2025_3536557
crossref_primary_10_1109_JSAC_2022_3221977
crossref_primary_10_1109_TCSVT_2025_3546765
crossref_primary_10_1007_s00530_025_01935_x
crossref_primary_10_1109_TCSVT_2022_3216713
crossref_primary_10_1109_TGRS_2024_3465043
crossref_primary_10_1109_TCSVT_2022_3229701
crossref_primary_10_1007_s11760_025_03826_0
crossref_primary_10_1016_j_neucom_2022_07_065
crossref_primary_10_1109_TIP_2022_3159477
crossref_primary_10_1109_LWC_2024_3429295
crossref_primary_10_1109_TAES_2023_3332056
crossref_primary_10_1109_TCSVT_2024_3371686
crossref_primary_10_1109_TCSVT_2025_3539747
crossref_primary_10_1109_JSAIT_2024_3393429
crossref_primary_10_1109_JPROC_2024_3520707
crossref_primary_10_1109_ACCESS_2023_3323873
crossref_primary_10_1109_TCSVT_2022_3164059
crossref_primary_10_1109_MWC_017_2100705
crossref_primary_10_1109_TCSVT_2025_3525664
crossref_primary_10_1016_j_image_2021_116544
crossref_primary_10_1109_JSTSP_2024_3491575
crossref_primary_10_1109_JSTSP_2024_3491576
crossref_primary_10_1109_TMM_2024_3416831
crossref_primary_10_1109_JSAC_2025_3531546
crossref_primary_10_1109_JSAC_2025_3560359
crossref_primary_10_1109_TMC_2025_3559584
crossref_primary_10_1109_TIP_2021_3138300
crossref_primary_10_1109_TPAMI_2023_3322904
crossref_primary_10_1109_MWC_005_2300574
crossref_primary_10_1109_TIP_2024_3515874
crossref_primary_10_1109_TAES_2024_3409524
Cites_doi 10.1007/978-3-642-45450-9
10.1109/tcom.1964.1088973
10.1109/icip.2019.8803120
10.1007/978-3-030-20876-9_45
10.1109/jstsp.2020.3043590
10.1007/978-3-030-01237-3_26
10.1126/science.1127647
10.1109/acssc.2003.1292216
10.1109/iccv.2019.00652
10.1109/tcsvt.2019.2892608
10.1093/comjnl/40.2_and_3.157
10.1109/TCSVT.2018.2880492
10.1109/icassp.2019.8683541
10.1109/18.532878
10.1109/pcs48520.2019.8954548
10.1109/cvpr42600.2020.00137
10.1007/s11554-018-0826-4
10.1002/j.1538-7305.1948.tb01340.x
10.1109/tip.2018.2817044
10.1007/978-3-030-04167-0_9
10.1109/cvpr.2019.01088
10.1109/iccv.2019.00324
10.1109/cvpr.2017.577
10.1109/dcc.2019.00008
10.1117/12.2555368
10.1109/cvprw50498.2020.00066
10.1109/tit.1972.1054906
10.1109/79.952802
10.1109/tip.2020.3036752
10.1109/icassp.2018.8462263
10.1109/tcom.1980.1094577
10.1109/pcs.2016.7906310
10.1109/cvpr.2018.00462
10.1109/tit.1982.1056489
10.1109/tit.1984.1056920
10.1109/TCSVT.2003.815173
10.1109/TMM.2019.2938345
10.1109/tit.1979.1056067
10.1109/access.2019.2911403
10.1109/tcsvt.2017.2734838
10.1109/PCS.2018.8456272
10.1145/3368405
10.1109/icip40778.2020.9190935
10.1109/cvpr.2018.00339
10.1109/tit.1960.1057548
10.1109/icip.2018.8451502
10.1109/icip.2019.8803413
10.1109/iccv.2019.00355
10.1109/cvpr.2019.01126
10.1109/tcsvt.2019.2910119
10.1109/MMSP.2018.8547064
10.1109/iccv.2019.00713
10.1109/tip.2020.2985225
10.1109/icip.2018.8451411
10.1109/icip40778.2020.9190860
10.1007/978-3-319-73600-6_6
10.1109/29.17498
10.1109/pcs.2016.7906399
10.1109/cvpr42600.2020.00853
10.1109/cvpr42600.2020.00796
10.1109/tpami.2020.2988453
10.1109/dcc.2019.00053
10.1109/pcs.2018.8456298
10.1007/s11263-020-01419-7
10.1109/iccv.2019.00031
10.1109/tmm.2019.2920603
10.1016/s0893-6080(05)80131-5
10.1109/tip.2019.2896489
10.1007/3-540-53504-7_63
10.1007/978-3-030-69538-5_36
10.1109/18.720541
10.1109/icmew46912.2020.9106022
10.1109/icip.2019.8803824
10.1007/978-1-4615-3626-0
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SP
8FD
H8D
L7M
DOI 10.1109/JSTSP.2020.3034501
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Technology Research Database
Aerospace Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Aerospace Database
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList Aerospace Database

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1941-0484
EndPage 353
ExternalDocumentID 10_1109_JSTSP_2020_3034501
9242247
Genre orig-research
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
ESBDL
F5P
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
RIA
RIE
RNS
AAYXX
CITATION
7SP
8FD
H8D
L7M
ID FETCH-LOGICAL-c339t-aeeb70d336e8f665b867bf43bf8b9432dbff1341f074011dd87c2b9fa1be963a3
IEDL.DBID RIE
ISICitedReferencesCount 139
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000622098600015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1932-4553
IngestDate Mon Jun 30 10:17:19 EDT 2025
Sat Nov 29 07:50:25 EST 2025
Tue Nov 18 21:07:00 EST 2025
Wed Aug 27 01:38:16 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c339t-aeeb70d336e8f665b867bf43bf8b9432dbff1341f074011dd87c2b9fa1be963a3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-0769-8985
0000-0002-7242-0210
OpenAccessLink https://ieeexplore.ieee.org/document/9242247
PQID 2493604543
PQPubID 75721
PageCount 15
ParticipantIDs ieee_primary_9242247
crossref_citationtrail_10_1109_JSTSP_2020_3034501
proquest_journals_2493604543
crossref_primary_10_1109_JSTSP_2020_3034501
PublicationCentury 2000
PublicationDate 2021-02-01
PublicationDateYYYYMMDD 2021-02-01
PublicationDate_xml – month: 02
  year: 2021
  text: 2021-02-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE journal of selected topics in signal processing
PublicationTitleAbbrev JSTSP
PublicationYear 2021
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref59
ref58
Ramachandran (ref38) 2017
ref53
Rippel (ref8) 2017; 70
ref54
Campos (ref94) 2019
Agustsson (ref9) 2017
MacQueen (ref19) 1967
Tschannen (ref108) 2018
Agustsson (ref29) 2020
Townsend (ref47) 2019
Klambauer (ref37) 2017
ref51
(ref42) 1992
Toderici (ref4) 2016
Theis (ref6) 2017
ref46
Bottou (ref16) 1994
ref41
ref44
ref43
(ref10) 2013
ref49
ref7
ref3
Minnen (ref28) 2018
ref100
ref101
Rezende (ref56) 2014; 32
Higgins (ref25) 2017
ref35
ref30
ref33
ref32
Lombardo (ref71) 2019
Clevert (ref36) 2016
ref24
ref23
Ball (ref27) 2018
Lee (ref76) 2019
ref20
ref22
ref21
Lee (ref99) 2019
Ball (ref39) 2016
Mentzer (ref110) 2020
ref13
ref15
ref14
ref96
ref11
Akyazi (ref89) 2019
ref17
ref18
Cover (ref12) 2006
Liu (ref60) 2019
ref93
Ball (ref48) 2018
ref92
ref95
Han (ref65) 2019
Dumoulin (ref50) 2017
ref91
ref90
ref86
ref85
ref88
Dosovitskiy (ref52) 2020
ref87
Hinton (ref45) 1993
Johnston (ref40) 2019
(ref34) 1993
Alemi (ref26) 2018; 80
ref82
ref81
ref84
ref83
ref80
ref79
ref78
ref109
ref106
ref107
ref75
ref104
ref74
ref105
ref77
ref102
Oktay (ref31) 2020
ref103
ref2
Ball (ref5) 2017
ref1
Kingma (ref55) 2014
ref70
ref112
ref73
ref72
ref68
ref67
Girod (ref115) 1993
ref69
ref64
ref63
ref116
ref66
ref113
ref114
Baig (ref97) 2017
Cao (ref98) 2020
Blau (ref111) 2019; 97
ref62
ref61
References_xml – ident: ref53
  doi: 10.1007/978-3-642-45450-9
– ident: ref23
  doi: 10.1109/tcom.1964.1088973
– ident: ref57
  doi: 10.1109/icip.2019.8803120
– ident: ref58
  doi: 10.1007/978-3-030-20876-9_45
– ident: ref73
  doi: 10.1109/jstsp.2020.3043590
– ident: ref64
  doi: 10.1007/978-3-030-01237-3_26
– volume-title: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops
  year: 2019
  ident: ref60
  article-title: Practical stacked non-local attention modules for image compression
– volume-title: Proc. 8th Int. Conf. Learn. Representations
  year: 2020
  ident: ref52
  article-title: You only train once: Loss-conditional training of deep networks
– ident: ref54
  doi: 10.1126/science.1127647
– volume-title: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops
  year: 2019
  ident: ref94
  article-title: Content adaptive optimization for neural image compression
– volume-title: Proc. 7th Int. Conf. Learn. Representations
  year: 2019
  ident: ref76
  article-title: Context-adaptive entropy model for end-to-end optimized image compression
– volume-title: Proc. 4th Int. Conf. Learn. Representations
  year: 2016
  ident: ref39
  article-title: Density modeling of images using a generalized normalization transformation
– ident: ref43
  doi: 10.1109/acssc.2003.1292216
– ident: ref70
  doi: 10.1109/iccv.2019.00652
– year: 2020
  ident: ref29
  article-title: Universally quantized neural compression
– ident: ref67
  doi: 10.1109/tcsvt.2019.2892608
– ident: ref46
  doi: 10.1093/comjnl/40.2_and_3.157
– ident: ref59
  doi: 10.1109/TCSVT.2018.2880492
– ident: ref95
  doi: 10.1109/icassp.2019.8683541
– volume-title: Proc. Adv Neural Inf. Process. Syst. 30
  year: 2017
  ident: ref97
  article-title: Learning to inpaint for image compression
– volume-title: Proc. Adv. Neural Inform. Process. Syst.
  year: 2018
  ident: ref28
  article-title: Joint autoregressive and hierarchical priors for learned image compression
– volume-title: Proc. 7th Int. Conf. Learn. Representat.
  year: 2019
  ident: ref65
  article-title: Deep probabilistic video compression
– ident: ref13
  doi: 10.1109/18.532878
– ident: ref109
  doi: 10.1109/pcs48520.2019.8954548
– ident: ref113
  doi: 10.1109/cvpr42600.2020.00137
– ident: ref100
  doi: 10.1007/s11554-018-0826-4
– ident: ref21
  doi: 10.1002/j.1538-7305.1948.tb01340.x
– volume-title: Proc. 8th Int. Conf. Learn. Representations
  year: 2020
  ident: ref31
  article-title: Scalable model compression by entropy penalized reparameterization
– ident: ref83
  doi: 10.1109/tip.2018.2817044
– ident: ref96
  doi: 10.1007/978-3-030-04167-0_9
– ident: ref92
  doi: 10.1109/cvpr.2019.01088
– year: 2013
  ident: ref10
  article-title: ITU-R rec. H.265 & ISO/IEC 23008-2: High efficiency video coding
– ident: ref51
  doi: 10.1109/iccv.2019.00324
– ident: ref7
  doi: 10.1109/cvpr.2017.577
– volume-title: Proc. Adv. Neural Inform. Process. Syst.
  year: 2017
  ident: ref9
  article-title: Soft-to-hard vector quantization for end-to-end learning compressible representations
– ident: ref63
  doi: 10.1109/dcc.2019.00008
– ident: ref105
  doi: 10.1117/12.2555368
– ident: ref79
  doi: 10.1109/cvprw50498.2020.00066
– volume-title: Proc. 5th Int. Conf. Learn. Representations
  year: 2017
  ident: ref6
  article-title: Lossy image compression with compressive autoencoders
– ident: ref14
  doi: 10.1109/tit.1972.1054906
– ident: ref1
  doi: 10.1109/79.952802
– ident: ref102
  doi: 10.1109/tip.2020.3036752
– volume-title: Proc. 6th Int. Conf. Learn. Representations
  year: 2018
  ident: ref48
  article-title: Integer networks for data compression with latent-variable models
– ident: ref49
  doi: 10.1109/icassp.2018.8462263
– volume-title: Proc. 5th Int. Conf. Learn. Representations
  year: 2017
  ident: ref50
  article-title: A learned representation for artistic style
– volume: 70
  volume-title: Proc. 34th Int. Conf. Mach. Learn.
  year: 2017
  ident: ref8
  article-title: Real-time adaptive image compression
– volume-title: Proc. 6th Int. Conf. Learn. Representations
  year: 2018
  ident: ref27
  article-title: Variational image compression with a scale hyperprior
– ident: ref20
  doi: 10.1109/tcom.1980.1094577
– ident: ref24
  doi: 10.1109/pcs.2016.7906310
– ident: ref77
  doi: 10.1109/cvpr.2018.00462
– volume-title: Proc. 4th Int. Conf. Learn. Representations
  year: 2016
  ident: ref4
  article-title: Variable rate image compression with recurrent neural networks
– ident: ref17
  doi: 10.1109/tit.1982.1056489
– ident: ref15
  doi: 10.1109/tit.1984.1056920
– ident: ref41
  doi: 10.1109/TCSVT.2003.815173
– start-page: 207
  volume-title: Digital Images and Human Vision
  year: 1993
  ident: ref115
  article-title: What’s wrong with mean-squared error?
– ident: ref88
  doi: 10.1109/TMM.2019.2938345
– volume-title: Proc. Adv. Neural Inform. Process. Syst.
  year: 2017
  ident: ref37
  article-title: Self-normalizing neural networks
– volume-title: Proc. 2nd Int. Conf. Learn. Representations
  year: 2014
  ident: ref55
  article-title: Auto-encoding variational Bayes
– year: 2020
  ident: ref98
  article-title: Lossless image compression through super-resolution
– ident: ref22
  doi: 10.1109/tit.1979.1056067
– ident: ref90
  doi: 10.1109/access.2019.2911403
– ident: ref82
  doi: 10.1109/tcsvt.2017.2734838
– year: 2020
  ident: ref110
  article-title: High-fidelity generative image compression
– ident: ref35
  doi: 10.1109/PCS.2018.8456272
– volume: 80
  volume-title: Proc. 35th Int. Conf. Mach. Learning
  year: 2018
  ident: ref26
  article-title: Fixing a broken ELBO
– volume-title: Proc. 5th Int. Conf. Learn. Representations
  year: 2017
  ident: ref5
  article-title: End-to-end optimized image compression
– ident: ref91
  doi: 10.1145/3368405
– ident: ref33
  doi: 10.1109/icip40778.2020.9190935
– ident: ref93
  doi: 10.1109/cvpr.2018.00339
– ident: ref18
  doi: 10.1109/tit.1960.1057548
– ident: ref75
  doi: 10.1109/icip.2018.8451502
– ident: ref112
  doi: 10.1109/icip.2019.8803413
– start-page: 281
  volume-title: Proc. 5th Berkeley Symp. Math. Statist. Probability
  year: 1967
  ident: ref19
  article-title: Some methods for classification and analysis of multivariate observations
– ident: ref68
  doi: 10.1109/iccv.2019.00355
– volume-title: Proc. 5th Int. Conf. Learn. Representations
  year: 2017
  ident: ref25
  article-title: $\beta$-VAE: Learning basic visual concepts with a constrained variational framework
– ident: ref66
  doi: 10.1109/cvpr.2019.01126
– year: 2019
  ident: ref40
  article-title: Computationally efficient neural image compression
– ident: ref114
  doi: 10.1109/tcsvt.2019.2910119
– ident: ref103
  doi: 10.1109/MMSP.2018.8547064
– ident: ref69
  doi: 10.1109/iccv.2019.00713
– volume-title: Proc. Adv. Neural Inform. Process. Syst.
  year: 1993
  ident: ref45
  article-title: Autoencoders, minimum description length and Helmholtz free energy
– volume-title: Proc. Adv. Neural Inform. Process. Syst.
  year: 2018
  ident: ref108
  article-title: Deep generative models for distribution-preserving lossy compression
– ident: ref78
  doi: 10.1109/tip.2020.2985225
– ident: ref62
  doi: 10.1109/icip.2018.8451411
– ident: ref32
  doi: 10.1109/icip40778.2020.9190860
– volume-title: Elements Inf. Theory
  year: 2006
  ident: ref12
– ident: ref85
  doi: 10.1007/978-3-319-73600-6_6
– ident: ref11
  doi: 10.1109/29.17498
– year: 1992
  ident: ref42
  article-title: ITU-R rec. T.81 & ISO/IEC 10918-1: Digital compression and coding of continuous-tone still images
– ident: ref81
  doi: 10.1109/pcs.2016.7906399
– ident: ref30
  doi: 10.1109/cvpr42600.2020.00853
– ident: ref61
  doi: 10.1109/cvpr42600.2020.00796
– volume: 97
  volume-title: Proc. 36th Int. Conf. Mach. Learn.
  year: 2019
  ident: ref111
  article-title: Rethinking lossy compression: The rate-distortion-perception tradeoff
– volume-title: Proc. Adv. Neural Inform. Process. Syst.
  year: 2019
  ident: ref71
  article-title: Deep generative video compression
– ident: ref74
  doi: 10.1109/tpami.2020.2988453
– ident: ref87
  doi: 10.1109/dcc.2019.00053
– ident: ref106
  doi: 10.1109/pcs.2018.8456298
– ident: ref101
  doi: 10.1007/s11263-020-01419-7
– year: 2017
  ident: ref38
  article-title: Searching for activation functions
– volume: 32
  volume-title: Proc. 31st Int. Conf. Mach. Learn.
  year: 2014
  ident: ref56
  article-title: Stochastic backpropagation and approximative inference in deep generative models
– volume-title: Proc. Adv. Neural Inf. Process. Syst. 7
  year: 1994
  ident: ref16
  article-title: Convergence properties of the k-means algorithms
– ident: ref107
  doi: 10.1109/iccv.2019.00031
– ident: ref86
  doi: 10.1109/tmm.2019.2920603
– ident: ref3
  doi: 10.1016/s0893-6080(05)80131-5
– ident: ref84
  doi: 10.1109/tip.2019.2896489
– ident: ref44
  doi: 10.1007/3-540-53504-7_63
– ident: ref72
  doi: 10.1007/978-3-030-69538-5_36
– ident: ref116
  doi: 10.1109/18.720541
– ident: ref80
  doi: 10.1109/icmew46912.2020.9106022
– ident: ref104
  doi: 10.1109/icip.2019.8803824
– year: 2019
  ident: ref99
  article-title: A hybrid architecture of jointly learning image compression and quality enhancement with improved entropy minimization
– ident: ref2
  doi: 10.1007/978-1-4615-3626-0
– year: 1993
  ident: ref34
  article-title: Kodak lossless true color image suite (PhotoCD PCD0992)
– volume-title: Proc. 4th Int. Conf. Learn. Representations
  year: 2016
  ident: ref36
  article-title: Fast and accurate deep network learning by exponential linear units (ELUs)
– volume-title: Proc. 7th Int. Conf. Learn. Representations
  year: 2019
  ident: ref47
  article-title: Practical lossless compression with latent variables using bits back coding
– volume-title: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops
  year: 2019
  ident: ref89
  article-title: Learning-based image compression using convolutional autoencoder and wavelet decomposition
SSID ssj0057614
Score 2.6766415
SecondaryResourceType review_article
Snippet We review a class of methods that can be collected under the name nonlinear transform coding (NTC), which over the past few years have become competitive with...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 339
SubjectTerms Artificial neural networks
Codec
Coding
data compression
Distortion
Empirical analysis
Entropy
Image coding
Linear transformations
machine learning
Optimization
Optimization techniques
rate-distortion
source coding
Stochastic processes
transform coding
Transforms
unsupervised learning
Vector quantization
Title Nonlinear Transform Coding
URI https://ieeexplore.ieee.org/document/9242247
https://www.proquest.com/docview/2493604543
Volume 15
WOSCitedRecordID wos000622098600015&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
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1941-0484
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0057614
  issn: 1932-4553
  databaseCode: RIE
  dateStart: 20070101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LSgMxFL20xYUufFWxtcos3GnszCQzSZYiFhdSClbpbsgTBGmlD7_fJJMpgiK4m0UC4eRx75nkngNwxQ3RmBmGXPZmEdEpRVxxiRy9NZIzqUlwUXh9ouMxm834pAU321oYY0x4fGZu_We4y9cLtfG_yoaOK7iIQ9vQprSsa7WaU9elzVm8Qc4RKQrcFMikfOiW-PPEUcHcMdQUkyIawDRBKLiq_DiKQ3wZHfxvZIewH_PI5K6e-CNomfkx7H1TF-xCf1zLYIhlMm3S0-R-4YPVCbyMHqb3jyhaISCFMV8jYYykqca4NMyWZSFZSaUlWFomOcG5ltZ6aTabeoe9TGtGVS65FZk0bosJfAqd-WJuziBx-Q-nVlDOjCSOrAmrcs5UZggVDh3Rg6zBplJRJ9zbVbxXgS-kvAp4Vh7PKuLZg-ttn49aJePP1l2P4LZlBK8Hg2YKqriRVpVjh7j0MoG4_3uvc9jN_TOT8JB6AJ31cmMuYEd9rt9Wy8uwRr4AQoq28g
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dS8MwFL3MKagPfk1xc-oefNO6tkmb5FGGY-IsA6fsLTRpAoJssg9_v0maDkERfOtDAuHk497T5J4DcMUULhBVNDDZmw5wEZKASSYCQ2-VYFQU2LkovA5JltHJhI1qcLOuhVFKucdn6tZ-urv8YiZX9ldZ13AFE3HIBmwmGMdhWa1VnbsmcY78HXIc4CRBVYlMyLpmkT-PDBmMDUcNEU68BUwVhpyvyo_D2EWY_v7_xnYAez6T7NyVU38INTU9gt1v-oINaGWlEEY-74yrBLXTm9lwdQwv_ftxbxB4M4RAIsSWQa6UIGGBUKqoTtNE0JQIjZHQVDCM4kJobcXZdGg99qKioETGguk8EspsshydQH06m6pT6JgMiBGdE0aVwIau5VrGjMpIYZIbdPImRBU2XHqlcGtY8c4dYwgZd3hyiyf3eDbhet3no9TJ-LN1wyK4bunBa0K7mgLut9KCG36IUisUiFq_97qE7cH4aciHD9njGezE9tGJe1bdhvpyvlLnsCU_l2-L-YVbL1_38bo5
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%3Ajournal&rft.genre=article&rft.atitle=Nonlinear+Transform+Coding&rft.jtitle=IEEE+journal+of+selected+topics+in+signal+processing&rft.au=Balle%2C+Johannes&rft.au=Chou%2C+Philip+A&rft.au=Minnen%2C+David&rft.au=Singh%2C+Saurabh&rft.date=2021-02-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1932-4553&rft.eissn=1941-0484&rft.volume=15&rft.issue=2&rft.spage=339&rft_id=info:doi/10.1109%2FJSTSP.2020.3034501&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1932-4553&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1932-4553&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1932-4553&client=summon