End-to-End Optimized Versatile Image Compression With Wavelet-Like Transform

Built on deep networks, end-to-end optimized image compression has made impressive progress in the past few years. Previous studies usually adopt a compressive auto-encoder, where the encoder part first converts image into latent features, and then quantizes the features before encoding them into bi...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence Jg. 44; H. 3; S. 1247 - 1263
Hauptverfasser:	Ma, Haichuan, Liu, Dong, Yan, Ning, Li, Houqiang, Wu, Feng
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.03.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Bit rate Coders Coefficients Compression ratio Deep network end-to-end optimization Entropy coding Image coding Image compression lossless compression lossy compression Mathematical models Measurement Quantization (signal) Rate-distortion wavelet transform Wavelet transforms
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Built on deep networks, end-to-end optimized image compression has made impressive progress in the past few years. Previous studies usually adopt a compressive auto-encoder, where the encoder part first converts image into latent features, and then quantizes the features before encoding them into bits. Both the conversion and the quantization incur information loss, resulting in a difficulty to optimally achieve arbitrary compression ratio. We propose iWave++ as a new end-to-end optimized image compression scheme, in which iWave, a trained wavelet-like transform, converts images into coefficients without any information loss. Then the coefficients are optionally quantized and encoded into bits. Different from the previous schemes, iWave++ is versatile : a single model supports both lossless and lossy compression, and also achieves arbitrary compression ratio by simply adjusting the quantization scale. iWave++ also features a carefully designed entropy coding engine to encode the coefficients progressively, and a de-quantization module for lossy compression. Experimental results show that lossy iWave++ achieves state-of-the-art compression efficiency compared with deep network-based methods; on the Kodak dataset, lossy iWave++ leads to 17.34 percent bits saving over BPG; lossless iWave++ achieves comparable or better performance than FLIF. Our code and models are available at https://github.com/mahaichuan/Versatile-Image-Compression .
AbstractList	Built on deep networks, end-to-end optimized image compression has made impressive progress in the past few years. Previous studies usually adopt a compressive auto-encoder, where the encoder part first converts image into latent features, and then quantizes the features before encoding them into bits. Both the conversion and the quantization incur information loss, resulting in a difficulty to optimally achieve arbitrary compression ratio. We propose iWave++ as a new end-to-end optimized image compression scheme, in which iWave, a trained wavelet-like transform, converts images into coefficients without any information loss. Then the coefficients are optionally quantized and encoded into bits. Different from the previous schemes, iWave++ is versatile : a single model supports both lossless and lossy compression, and also achieves arbitrary compression ratio by simply adjusting the quantization scale. iWave++ also features a carefully designed entropy coding engine to encode the coefficients progressively, and a de-quantization module for lossy compression. Experimental results show that lossy iWave++ achieves state-of-the-art compression efficiency compared with deep network-based methods; on the Kodak dataset, lossy iWave++ leads to 17.34 percent bits saving over BPG; lossless iWave++ achieves comparable or better performance than FLIF. Our code and models are available at https://github.com/mahaichuan/Versatile-Image-Compression . Built on deep networks, end-to-end optimized image compression has made impressive progress in the past few years. Previous studies usually adopt a compressive auto-encoder, where the encoder part first converts image into latent features, and then quantizes the features before encoding them into bits. Both the conversion and the quantization incur information loss, resulting in a difficulty to optimally achieve arbitrary compression ratio. We propose iWave++ as a new end-to-end optimized image compression scheme, in which iWave, a trained wavelet-like transform, converts images into coefficients without any information loss. Then the coefficients are optionally quantized and encoded into bits. Different from the previous schemes, iWave++ is versatile: a single model supports both lossless and lossy compression, and also achieves arbitrary compression ratio by simply adjusting the quantization scale. iWave++ also features a carefully designed entropy coding engine to encode the coefficients progressively, and a de-quantization module for lossy compression. Experimental results show that lossy iWave++ achieves state-of-the-art compression efficiency compared with deep network-based methods; on the Kodak dataset, lossy iWave++ leads to 17.34 percent bits saving over BPG; lossless iWave++ achieves comparable or better performance than FLIF. Our code and models are available at https://github.com/mahaichuan/Versatile-Image-Compression.Built on deep networks, end-to-end optimized image compression has made impressive progress in the past few years. Previous studies usually adopt a compressive auto-encoder, where the encoder part first converts image into latent features, and then quantizes the features before encoding them into bits. Both the conversion and the quantization incur information loss, resulting in a difficulty to optimally achieve arbitrary compression ratio. We propose iWave++ as a new end-to-end optimized image compression scheme, in which iWave, a trained wavelet-like transform, converts images into coefficients without any information loss. Then the coefficients are optionally quantized and encoded into bits. Different from the previous schemes, iWave++ is versatile: a single model supports both lossless and lossy compression, and also achieves arbitrary compression ratio by simply adjusting the quantization scale. iWave++ also features a carefully designed entropy coding engine to encode the coefficients progressively, and a de-quantization module for lossy compression. Experimental results show that lossy iWave++ achieves state-of-the-art compression efficiency compared with deep network-based methods; on the Kodak dataset, lossy iWave++ leads to 17.34 percent bits saving over BPG; lossless iWave++ achieves comparable or better performance than FLIF. Our code and models are available at https://github.com/mahaichuan/Versatile-Image-Compression.
Author	Ma, Haichuan Yan, Ning Wu, Feng Li, Houqiang Liu, Dong
Author_xml	– sequence: 1 givenname: Haichuan orcidid: 0000-0003-1126-9382 surname: Ma fullname: Ma, Haichuan email: hcma@mail.ustc.edu.cn organization: CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China – sequence: 2 givenname: Dong orcidid: 0000-0001-9100-2906 surname: Liu fullname: Liu, Dong email: dongeliu@ustc.edu.cn organization: CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China – sequence: 3 givenname: Ning orcidid: 0000-0002-6771-111X surname: Yan fullname: Yan, Ning email: nyan@mail.ustc.edu.cn organization: CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China – sequence: 4 givenname: Houqiang orcidid: 0000-0003-2188-3028 surname: Li fullname: Li, Houqiang email: lihq@ustc.edu.cn organization: CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China – sequence: 5 givenname: Feng surname: Wu fullname: Wu, Feng email: fengwu@ustc.edu.cn organization: CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, University of Science and Technology of China, Hefei, China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/32966210$$D View this record in MEDLINE/PubMed
BookMark	eNp9kcFOGzEQhi0EKoH2BUCqVuLSywZ77HXsI4poGykIDqEcLe_uuDXsrlPbQaJP300TeuDAaS7f92tm_hNyOIQBCTljdMoY1Zeru6ubxRQo0CmnICnlB2QCTNJSg4ZDMqFMQqkUqGNyktIjpUxUlH8gxxy0lMDohCyvh7bMoRxHcbvOvvd_sC1-YEw2-w6LRW9_YjEP_TpiSj4MxYPPv4oH-4wd5nLpn7BYRTskF2L_kRw52yX8tJ-n5P7r9Wr-vVzeflvMr5ZlwyuWS6ekExo5Z7KesZmum9pZ5jSXigvtnG0pawHHQxrXKkChFLNSuFro2jbI-Cn5sstdx_B7gymb3qcGu84OGDbJgBCVnlVawIhevEEfwyYO43YGJFRcSs22gZ_31KbusTXr6HsbX8zrn0ZA7YAmhpQiOtP4PH4oDDla3xlGzbYS868Ss63E7CsZVXijvqa_K53vJI-I_wUNVMy05n8B70uViQ
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1109_TAI_2023_3340982 crossref_primary_10_1109_ACCESS_2023_3349351 crossref_primary_10_1109_ACCESS_2024_3350643 crossref_primary_10_1109_TCSVT_2022_3222418 crossref_primary_10_1109_TMI_2022_3212780 crossref_primary_10_1109_TIP_2023_3276333 crossref_primary_10_1109_TPAMI_2021_3065339 crossref_primary_10_1109_ACCESS_2025_3597008 crossref_primary_10_1109_TGRS_2023_3315725 crossref_primary_10_1109_ACCESS_2024_3396407 crossref_primary_10_1016_j_ress_2025_111371 crossref_primary_10_1109_TIP_2022_3184845 crossref_primary_10_1109_TCSVT_2024_3465445 crossref_primary_10_1007_s00530_023_01192_w crossref_primary_10_1016_j_engappai_2025_110982 crossref_primary_10_1049_ell2_12586 crossref_primary_10_1002_cta_4135 crossref_primary_10_1016_j_imavis_2024_105073 crossref_primary_10_1109_TCSVT_2023_3253702 crossref_primary_10_1109_TMM_2025_3535279 crossref_primary_10_1007_s11042_025_20687_4 crossref_primary_10_1109_TIP_2025_3550013 crossref_primary_10_1117_1_JRS_18_036508 crossref_primary_10_1007_s11263_021_01491_7 crossref_primary_10_1109_TII_2024_3431018 crossref_primary_10_1109_TCSVT_2024_3415823 crossref_primary_10_1016_j_dsp_2023_104339 crossref_primary_10_1109_ACCESS_2021_3137345 crossref_primary_10_1109_TIP_2024_3378910 crossref_primary_10_3390_s24165439 crossref_primary_10_1080_13682199_2025_2499390 crossref_primary_10_1016_j_sigpro_2022_108778 crossref_primary_10_1145_3652148 crossref_primary_10_1109_TCSVT_2023_3310188 crossref_primary_10_1109_TCSVT_2023_3316834 crossref_primary_10_1109_TCE_2024_3485179 crossref_primary_10_1007_s12652_024_04858_z crossref_primary_10_1109_TIP_2024_3349859 crossref_primary_10_1007_s11263_023_01809_7 crossref_primary_10_1109_TBC_2024_3464413 crossref_primary_10_1109_TBDATA_2022_3201176 crossref_primary_10_1109_TIP_2024_3477356 crossref_primary_10_1145_3719011 crossref_primary_10_1109_JSEN_2025_3569520 crossref_primary_10_1145_3649503 crossref_primary_10_1109_TCSVT_2023_3237274 crossref_primary_10_1109_TCSVT_2023_3303228 crossref_primary_10_3390_rs16193594 crossref_primary_10_1109_TCSVT_2024_3371178 crossref_primary_10_1109_TCSVT_2024_3376704 crossref_primary_10_1109_TCSVT_2024_3401872 crossref_primary_10_1016_j_eswa_2024_125535 crossref_primary_10_1007_s40747_023_01119_y crossref_primary_10_1109_TPAMI_2023_3348486 crossref_primary_10_3390_computation11100191 crossref_primary_10_1145_3631710 crossref_primary_10_1109_TBC_2024_3443470 crossref_primary_10_1007_s00521_024_09660_8 crossref_primary_10_1109_TBC_2025_3565895 crossref_primary_10_1109_TPAMI_2022_3185316 crossref_primary_10_1109_TCSVT_2025_3546765 crossref_primary_10_7717_peerj_cs_1924 crossref_primary_10_1016_j_image_2024_117227 crossref_primary_10_1109_TIP_2023_3333279 crossref_primary_10_1109_TCSVT_2024_3360248 crossref_primary_10_1049_ipr2_70080 crossref_primary_10_1109_TCSVT_2022_3216713 crossref_primary_10_1016_j_eswa_2023_121299 crossref_primary_10_1109_TCSVT_2022_3229701 crossref_primary_10_3390_fi16080297 crossref_primary_10_1016_j_neucom_2022_07_065 crossref_primary_10_1109_TMM_2021_3130754 crossref_primary_10_1007_s00371_024_03428_w crossref_primary_10_1109_TCSVT_2024_3395275 crossref_primary_10_1109_TIP_2022_3160072 crossref_primary_10_1109_ACCESS_2023_3323873 crossref_primary_10_1109_ACCESS_2024_3514215 crossref_primary_10_3389_fpls_2022_901042 crossref_primary_10_1007_s10489_023_05047_9 crossref_primary_10_1109_TPAMI_2024_3356557 crossref_primary_10_1016_j_aei_2024_102669 crossref_primary_10_1109_TCSVT_2023_3317424 crossref_primary_10_3390_e26050357 crossref_primary_10_1109_JETCAS_2025_3538652 crossref_primary_10_1109_TBC_2025_3587532 crossref_primary_10_1007_s00530_025_01945_9 crossref_primary_10_1109_TIP_2023_3319275 crossref_primary_10_1109_TCSVT_2025_3556708 crossref_primary_10_1109_TIP_2024_3482877 crossref_primary_10_1109_TGRS_2023_3349306 crossref_primary_10_1109_TPAMI_2023_3322904 crossref_primary_10_1109_TIP_2023_3263099 crossref_primary_10_1109_TMM_2022_3220421 crossref_primary_10_1117_1_APN_3_3_036005
Cites_doi	10.1109/CVPRW.2017.151 10.1109/ICCV.2019.00031 10.1109/ICASSP.2018.8462263 10.1109/DCC.1993.253128 10.1109/TIP.2003.817237 10.1109/CVPR.2018.00461 10.1109/30.920468 10.1162/neco.1997.9.8.1735 10.1109/CVPR.2017.577 10.1109/TCSVT.2012.2221191 10.1109/CVPRW.2017.150 10.1109/83.847830 10.1080/2165347X.2015.1024298 10.1109/ICIP.2017.8296236 10.1109/CVPR.2018.00462 10.1006/acha.1996.0015 10.1109/CVPR.2019.01088 10.1109/TMM.2019.2957990 10.1109/76.499834 10.1126/science.1127647 10.1007/BF02476026 10.1109/TCSVT.2003.815165 10.1109/CVPR.2018.00339 10.1109/ICCV.2019.00324 10.1109/PCS.2016.7906310 10.1109/TCSVT.2018.2880492 10.1109/ICIP.2016.7532320 10.1007/978-3-319-51811-4_3
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TPAMI.2020.3026003
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitle	CrossRef PubMed Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitleList	Technology Research Database PubMed MEDLINE - Academic
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	2160-9292 1939-3539
EndPage	1263
ExternalDocumentID	32966210 10_1109_TPAMI_2020_3026003 9204799
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: National Key Research and Development Program of China grantid: 2018YFA0701603 funderid: 10.13039/501100012166 – fundername: National Natural Science Foundation of China; Natural Science Foundation of China grantid: 61772483; 61931014 funderid: 10.13039/501100001809
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 AAYXX CITATION 5VS 9M8 AAYOK ABFSI ADRHT AETIX AGSQL AI. AIBXA ALLEH FA8 H~9 IBMZZ ICLAB IFJZH NPM PKN RIC RIG RNI RZB VH1 XJT Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c351t-f86f49e3316b7179bcbfa1f9368349ffad01d2e160cfd82e4881a64fb49bace13
IEDL.DBID	RIE
ISICitedReferencesCount	130
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000752018000014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828 1939-3539
IngestDate	Sun Sep 28 10:35:49 EDT 2025 Mon Jun 30 07:18:33 EDT 2025 Wed Feb 19 02:28:07 EST 2025 Sat Nov 29 05:15:59 EST 2025 Tue Nov 18 22:34:45 EST 2025 Wed Aug 27 03:00:15 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	3
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c351t-f86f49e3316b7179bcbfa1f9368349ffad01d2e160cfd82e4881a64fb49bace13
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0003-1126-9382 0000-0002-6771-111X 0000-0001-9100-2906 0000-0003-2188-3028
PMID	32966210
PQID	2625366911
PQPubID	85458
PageCount	17
ParticipantIDs	crossref_citationtrail_10_1109_TPAMI_2020_3026003 proquest_journals_2625366911 ieee_primary_9204799 proquest_miscellaneous_2445975942 pubmed_primary_32966210 crossref_primary_10_1109_TPAMI_2020_3026003
PublicationCentury	2000
PublicationDate	2022-03-01
PublicationDateYYYYMMDD	2022-03-01
PublicationDate_xml	– month: 03 year: 2022 text: 2022-03-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev	TPAMI
PublicationTitleAlternate	IEEE Trans Pattern Anal Mach Intell
PublicationYear	2022
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	ref13 ref12 ref15 minnen (ref6) 2018 ref10 theis (ref8) 2017 ref17 ref16 ref18 zaremba (ref40) 2014 liu (ref21) 2019 ref46 ref45 ref48 ref41 ref44 ballé (ref1) 2016 ref43 ho (ref32) 2019 jacobsen (ref35) 2018 ref49 salimans (ref30) 2017 lipton (ref39) 2015 ref9 ref4 ref3 ref5 lee (ref50) 2018 rippel (ref7) 2017 agustsson (ref25) 2017 ref34 ref37 ref36 ref31 lee (ref51) 2019 ref38 liu (ref22) 2019 kingma (ref47) 2014 van den oord (ref29) 2016 ballé (ref2) 2018 lee (ref24) 2019 zhou (ref23) 2019 ref26 van den oord (ref28) 2016 ref20 ref27 li (ref42) 2018 hinton (ref11) 2006; 313 wiegand (ref14) 2003; 13 toderici (ref19) 2015 hoogeboom (ref33) 2019
References_xml	– ident: ref43 doi: 10.1109/CVPRW.2017.151 – year: 2018 ident: ref50 article-title: Context-adaptive entropy model for end-to-end optimized image compression – year: 2019 ident: ref32 article-title: Compression with flows via local bits-back coding – ident: ref10 doi: 10.1109/ICCV.2019.00031 – ident: ref27 doi: 10.1109/ICASSP.2018.8462263 – ident: ref36 doi: 10.1109/DCC.1993.253128 – ident: ref34 doi: 10.1109/TIP.2003.817237 – year: 2019 ident: ref51 article-title: An end-to-end joint learning scheme of image compression and quality enhancement with improved entropy minimization – ident: ref3 doi: 10.1109/CVPR.2018.00461 – ident: ref13 doi: 10.1109/30.920468 – ident: ref41 doi: 10.1162/neco.1997.9.8.1735 – year: 2015 ident: ref19 article-title: Variable rate image compression with recurrent neural networks – ident: ref9 doi: 10.1109/CVPR.2017.577 – start-page: 1747 year: 2016 ident: ref28 article-title: Pixel recurrent neural networks publication-title: Proc 33rd Int Conf Mach Learn – ident: ref15 doi: 10.1109/TCSVT.2012.2221191 – ident: ref46 doi: 10.1109/CVPRW.2017.150 – ident: ref38 doi: 10.1109/83.847830 – start-page: 1 year: 2019 ident: ref23 article-title: Multi-scale and context-adaptive entropy model for image compression publication-title: Proc IEEE/CVF Conf Comput Vis Pattern Recognit Workshops – start-page: 4790 year: 2016 ident: ref29 article-title: Conditional image generation with PixelCNN decoders publication-title: Proc 30th Int Conf Neural Inf Process Syst – ident: ref48 doi: 10.1080/2165347X.2015.1024298 – ident: ref45 doi: 10.1109/ICIP.2017.8296236 – ident: ref5 doi: 10.1109/CVPR.2018.00462 – ident: ref17 doi: 10.1006/acha.1996.0015 – start-page: 1 year: 2019 ident: ref24 article-title: Extended end-to-end optimized image compression method based on a context-adaptive entropy model publication-title: Proc IEEE/CVF Conf Comput Vis Pattern Recognit Workshops – ident: ref31 doi: 10.1109/CVPR.2019.01088 – start-page: 2922 year: 2017 ident: ref7 article-title: Real-time adaptive image compression publication-title: Proc 34th Int Conf Mach Learn – ident: ref16 doi: 10.1109/TMM.2019.2957990 – start-page: 10 794 year: 2018 ident: ref6 article-title: Joint autoregressive and hierarchical priors for learned image compression publication-title: Proc 32nd Int Conf Neural Inf Process Syst – year: 2014 ident: ref47 article-title: Adam: A method for stochastic optimization – year: 2015 ident: ref39 article-title: A critical review of recurrent neural networks for sequence learning – ident: ref37 doi: 10.1109/76.499834 – year: 2014 ident: ref40 article-title: Recurrent neural network regularization – volume: 313 start-page: 504 year: 2006 ident: ref11 article-title: Reducing the dimensionality of data with neural networks publication-title: Science doi: 10.1126/science.1127647 – year: 2019 ident: ref21 article-title: Non-local attention optimized deep image compression – ident: ref18 doi: 10.1007/BF02476026 – year: 2018 ident: ref2 article-title: Variational image compression with a scale hyperprior – start-page: 1 year: 2019 ident: ref22 article-title: Practical stacked non-local attention modules for image compression publication-title: Proc IEEE/CVF Conf Comput Vis Pattern Recognit Workshops – volume: 13 start-page: 560 year: 2003 ident: ref14 article-title: overview of the h.264/avc video coding standard publication-title: IEEE Transactions on Circuits and Systems for Video Technology doi: 10.1109/TCSVT.2003.815165 – year: 2018 ident: ref42 article-title: Enlarging context with low cost: Efficient arithmetic coding with trimmed convolution – start-page: 1141 year: 2017 ident: ref25 article-title: Soft-to-hard vector quantization for end-to-end learning compressible representations publication-title: Proc 31st Int Conf Neural Inf Process Syst – year: 2017 ident: ref8 article-title: Lossy image compression with compressive autoencoders – ident: ref4 doi: 10.1109/CVPR.2018.00339 – year: 2017 ident: ref30 article-title: PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications – ident: ref12 doi: 10.1109/ICCV.2019.00324 – year: 2018 ident: ref35 article-title: i-RevNet: Deep invertible networks – year: 2019 ident: ref33 article-title: Integer discrete flows and lossless compression – ident: ref20 doi: 10.1109/PCS.2016.7906310 – ident: ref26 doi: 10.1109/TCSVT.2018.2880492 – ident: ref49 doi: 10.1109/ICIP.2016.7532320 – ident: ref44 doi: 10.1007/978-3-319-51811-4_3 – year: 2016 ident: ref1 article-title: End-to-end optimized image compression
SSID	ssj0014503
Score	2.6820345
Snippet	Built on deep networks, end-to-end optimized image compression has made impressive progress in the past few years. Previous studies usually adopt a compressive...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1247
SubjectTerms	Bit rate Coders Coefficients Compression ratio Deep network end-to-end optimization Entropy coding Image coding Image compression lossless compression lossy compression Mathematical models Measurement Quantization (signal) Rate-distortion wavelet transform Wavelet transforms
Title	End-to-End Optimized Versatile Image Compression With Wavelet-Like Transform
URI	https://ieeexplore.ieee.org/document/9204799 https://www.ncbi.nlm.nih.gov/pubmed/32966210 https://www.proquest.com/docview/2625366911 https://www.proquest.com/docview/2445975942
Volume	44
WOSCitedRecordID	wos000752018000014&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: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB61FQc4UGh5BEplJG5gmtiONz5WqBWVltLDou4tcuyxuqLNojbLgV_P2HmoB0DiFCtxHso3Y894PPMBvHPKo8Tcc2uc4UqjolZecR98ZAgsUdlUXX8-Oz-vlktzsQUfplwYREybz_BjbKZYvl-7TVwqOzIiFkQ327A9m-k-V2uKGKgysSCTBUMaTm7EmCCTm6PFxfGXM3IFBXmosYRWHslzpCBDX8TE2XvzUSJY-butmeac093_-9on8HiwLdlxLwxPYQvbPdgdeRvYoMZ78OheEcJ9mJ-0nndrTgf2lQaQm9Uv9CyuoxFo18jObmjIYfEp_ZbZll2uuit2aSNlRcfnq-_IFqP5-wy-nZ4sPn3mA8cCd7IsOh4qHZRBgkU35NmZxjXBFsFIXUllQrA-L7zAQucu-Eog6XthtQqNMo11WMjnsNOuW3wJjIYqgZ7OO-1VZSPXlZROa8QyRrd1BsX4p2s3FCCPPBjXdXJEclMnoOoIVD0AlcH76Z4fffmNf_bejzBMPQcEMjgYAa0HDb2rBTl-Umsa6zN4O10m3YoBE9viekN9lCJ_qzRKZPCiF4Tp2aP8vPrzO1_DQxETJdJutQPY6W43-AYeuJ_d6u72kAR4WR0mAf4N4wHolw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VgkQ5UGgpBAoYiRuYJrZj4mOFWnVFuvSwqL1FiT0WK9osarMc-PWMnYd6ACROsRLnoXwz9ozHMx_AW6scSkwdr401XGlU1EoL7rwLDIE5qjpW1y8_zufFxYU524D3Uy4MIsbNZ_ghNGMs363sOiyVHRgRCqKbO3A3V0qkfbbWFDNQeeRBJhuGdJwciTFFJjUHi7PD0xk5g4J81FBEKw30OVKQqS9C6uytGSlSrPzd2oyzzvH2_33vI3g4WJfssBeHx7CB7Q5sj8wNbFDkHXhwqwzhLpRHrePditOBfaEh5Gr5Cx0LK2kE2yWy2RUNOiw8pd8027LzZfeNndeBtKLj5fI7ssVoAD-Br8dHi08nfGBZ4FbmWcd9ob0ySMDohnw709jG15k3UhdSGe9rl2ZOYKZT610hkDQ-q7XyjTJNbTGTe7DZrlp8BowGK4GOzlvtVFEHtisprdaIeYhv6wSy8U9XdihBHpgwLqvoiqSmikBVAahqACqBd9M9P_oCHP_svRtgmHoOCCSwPwJaDTp6Uwly_aTWNNon8Ga6TNoVQiZ1i6s19VGKPK7cKJHA014QpmeP8vP8z-98DfdPFqdlVc7mn1_AlghpE3Hv2j5sdtdrfAn37M9ueXP9Korxb6kE6vY
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=End-to-End+Optimized+Versatile+Image+Compression+With+Wavelet-Like+Transform&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Ma%2C+Haichuan&rft.au=Liu%2C+Dong&rft.au=Yan%2C+Ning&rft.au=Li%2C+Houqiang&rft.date=2022-03-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0162-8828&rft.eissn=1939-3539&rft.volume=44&rft.issue=3&rft.spage=1247&rft_id=info:doi/10.1109%2FTPAMI.2020.3026003&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon