PyCIL: A Python Toolbox for Class-Incremental Learning

Traditional machine learning systems are deployed under the closed-world setting, which requires the entire training data before the offline training process. However, real-world applications often face the incoming new classes, and a model should incorporate them continually. The learning paradigm...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Zhou, Da-Wei, Wang, Fu-Yun, Ye, Han-Jia, Zhan, De-Chuan
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 26.10.2022
Subjects
Online AccessGet full text
ISSN2331-8422
DOI10.48550/arxiv.2112.12533

Cover

Abstract Traditional machine learning systems are deployed under the closed-world setting, which requires the entire training data before the offline training process. However, real-world applications often face the incoming new classes, and a model should incorporate them continually. The learning paradigm is called Class-Incremental Learning (CIL). We propose a Python toolbox that implements several key algorithms for class-incremental learning to ease the burden of researchers in the machine learning community. The toolbox contains implementations of a number of founding works of CIL such as EWC and iCaRL, but also provides current state-of-the-art algorithms that can be used for conducting novel fundamental research. This toolbox, named PyCIL for Python Class-Incremental Learning, is available at https://github.com/G-U-N/PyCIL
AbstractList Traditional machine learning systems are deployed under the closed-world setting, which requires the entire training data before the offline training process. However, real-world applications often face the incoming new classes, and a model should incorporate them continually. The learning paradigm is called Class-Incremental Learning (CIL). We propose a Python toolbox that implements several key algorithms for class-incremental learning to ease the burden of researchers in the machine learning community. The toolbox contains implementations of a number of founding works of CIL such as EWC and iCaRL, but also provides current state-of-the-art algorithms that can be used for conducting novel fundamental research. This toolbox, named PyCIL for Python Class-Incremental Learning, is available at https://github.com/G-U-N/PyCIL
Traditional machine learning systems are deployed under the closed-world setting, which requires the entire training data before the offline training process. However, real-world applications often face the incoming new classes, and a model should incorporate them continually. The learning paradigm is called Class-Incremental Learning (CIL). We propose a Python toolbox that implements several key algorithms for class-incremental learning to ease the burden of researchers in the machine learning community. The toolbox contains implementations of a number of founding works of CIL such as EWC and iCaRL, but also provides current state-of-the-art algorithms that can be used for conducting novel fundamental research. This toolbox, named PyCIL for Python Class-Incremental Learning, is available at https://github.com/G-U-N/PyCIL
Author Han-Jia, Ye
Da-Wei, Zhou
De-Chuan, Zhan
Fu-Yun, Wang
Author_xml – sequence: 1
  givenname: Da-Wei
  surname: Zhou
  fullname: Zhou, Da-Wei
– sequence: 2
  givenname: Fu-Yun
  surname: Wang
  fullname: Wang, Fu-Yun
– sequence: 3
  givenname: Han-Jia
  surname: Ye
  fullname: Ye, Han-Jia
– sequence: 4
  givenname: De-Chuan
  surname: Zhan
  fullname: Zhan, De-Chuan
BackLink https://doi.org/10.1007/s11432-022-3600-y$$DView published paper (Access to full text may be restricted)
https://doi.org/10.48550/arXiv.2112.12533$$DView paper in arXiv
BookMark eNotz0FPgzAYxvHGaOKc-wCebOIZbPu2tHhbiFMSEnfgTkopysLaWZgZ317cPL2XX948_zt07byzCD1QEnMlBHnW4dT9xIxSFlMmAK7QggHQSHHGbtFqGHaEEJZIJgQsULKdsrx4wWu8ncYv73DpfV_7E259wFmvhyHKnQl2b92oe1xYHVznPu_RTav7wa7-7xKVm9cye4-Kj7c8WxeRFgwiAKF4w5VtWw6klVCDrI1MrTICDDRJQmpVW9CcmUa06SwUEWbmJpU6rWGJHi9vz1HVIXR7HabqL646x83i6SIOwX8f7TBWO38Mbt5UsYQCp5JTgF9KOlI6
ContentType Paper
Journal Article
Copyright 2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
http://arxiv.org/licenses/nonexclusive-distrib/1.0
Copyright_xml – notice: 2022. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: http://arxiv.org/licenses/nonexclusive-distrib/1.0
DBID 8FE
8FG
ABJCF
ABUWG
AFKRA
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
HCIFZ
L6V
M7S
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
AKY
GOX
DOI 10.48550/arxiv.2112.12533
DatabaseName ProQuest SciTech Collection
ProQuest Technology Collection
Materials Science & Engineering Collection
ProQuest Central (Alumni)
ProQuest Central
ProQuest Central Essentials - QC
ProQuest Central
Technology Collection
ProQuest One Community College
ProQuest Central
SciTech Premium Collection
ProQuest Engineering Collection
Engineering Database
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering Collection
arXiv Computer Science
arXiv.org
DatabaseTitle Publicly Available Content Database
Engineering Database
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest One Academic UKI Edition
ProQuest Central Korea
Materials Science & Engineering Collection
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
Engineering Collection
DatabaseTitleList Publicly Available Content Database

Database_xml – sequence: 1
  dbid: GOX
  name: arXiv.org
  url: http://arxiv.org/find
  sourceTypes: Open Access Repository
– sequence: 2
  dbid: 8FG
  name: ProQuest Technology Collection
  url: https://search.proquest.com/technologycollection1
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Physics
EISSN 2331-8422
ExternalDocumentID 2112_12533
Genre Working Paper/Pre-Print
GroupedDBID 8FE
8FG
ABJCF
ABUWG
AFKRA
ALMA_UNASSIGNED_HOLDINGS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
FRJ
HCIFZ
L6V
M7S
M~E
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
AKY
GOX
ID FETCH-LOGICAL-a523-33584d48eff430f73b37bc79e8c53c3d660b8be3a42cd5f9f73805ceffc97a9b3
IEDL.DBID GOX
IngestDate Tue Jul 22 23:01:55 EDT 2025
Mon Jun 30 09:21:27 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a523-33584d48eff430f73b37bc79e8c53c3d660b8be3a42cd5f9f73805ceffc97a9b3
Notes SourceType-Working Papers-1
ObjectType-Working Paper/Pre-Print-1
content type line 50
OpenAccessLink https://arxiv.org/abs/2112.12533
PQID 2613417413
PQPubID 2050157
ParticipantIDs arxiv_primary_2112_12533
proquest_journals_2613417413
PublicationCentury 2000
PublicationDate 20221026
PublicationDateYYYYMMDD 2022-10-26
PublicationDate_xml – month: 10
  year: 2022
  text: 20221026
  day: 26
PublicationDecade 2020
PublicationPlace Ithaca
PublicationPlace_xml – name: Ithaca
PublicationTitle arXiv.org
PublicationYear 2022
Publisher Cornell University Library, arXiv.org
Publisher_xml – name: Cornell University Library, arXiv.org
SSID ssj0002672553
Score 1.8141227
SecondaryResourceType preprint
Snippet Traditional machine learning systems are deployed under the closed-world setting, which requires the entire training data before the offline training process....
Traditional machine learning systems are deployed under the closed-world setting, which requires the entire training data before the offline training process....
SourceID arxiv
proquest
SourceType Open Access Repository
Aggregation Database
SubjectTerms Algorithms
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Machine learning
Training
SummonAdditionalLinks – databaseName: ProQuest Technology Collection
  dbid: 8FG
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LTwIxEG4UYuLNZ0DR9OC1QPra1osxRESjhgMm3DZ9rTEhLAIa-PdOy6IHE6_b7qGz3W--mWnnQ-iKWiptwSxR0jsIUHhGtAEwlNRz6oGTUxMrus8vcvDKH8diXCXcFtWxyi0mJqD2pYs58g4wfQBc8H_sZvZBompUrK5WEhq7qA6OWsddrfr3PzkWKjNgzGxTzEytuzpmvnr_akPUQ9vwRpTLradHf6A4-Zf-AaoPzSzMD9FOmB6hvXQs0y2OkRyuew9P1_gWD9fxkj8eleXElisMVBMnPUsCP_gmxWcmuGqW-naCRv27UW9AKqUDYiAQJIwBDfBchaLgrFtkzLLMukwH5QRzzEvZtcoGZjh1XhQaZqiucDDd6cxoy05RbVpOQwNhIFA0UC6MgsBKeKG8LbjQVnBXRG_dRI203ny2aWaRR1PkyRRN1NqaIK828iL_NfvZ_8PnaJ_GmwEA61S2UG05_wwX4K-X9jJ9lG_gFpJN
  priority: 102
  providerName: ProQuest
Title PyCIL: A Python Toolbox for Class-Incremental Learning
URI https://www.proquest.com/docview/2613417413
https://arxiv.org/abs/2112.12533
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdV09TwJBEJ0ANjZGowYUyRa2p2S_bs8OCYhGkBhM6C77aUyMGEEDjb_dub0jFsZmi8tMcbN3897b3ZkFOKeGShOYSZR0FgUKT5NMYzKU1HHqkJNTXezojidy9MTv5mJeA7KthdEf65evsj-wWV6iOqEXCMGM1aGORKEo5n2Yl5uTsRVXZf9rhxwzPvqTWiNeDPdhryJ6pFfOzAHU_NshyOmmf3t_RXpkuimK9slssXg1izVB6kji_ZQJ_rDlkh06V81Pn49gNhzM-qOkurkg0SjsEsYQ1h1XPgTOuiFlhqXGpplXVjDLnJRdo4xnmlPrRMjQQnWFRXObpToz7BgaKP59EwgSIuopF1qhUBJOKGcCF5kR3IYCfVvQjO-bv5fNKfIiFHkMRQva2xDk1Ye5zFEwIW4hjWAn_3uewi4tTvljiqayDY3Vx6c_Q-xdmQ7U1fCmAzvXg8n0sROnA8fx9-AH9i-FVQ
linkProvider Cornell University
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LS8NAEB5qi-jNJ9ZnDnqMln0lEYr4pNVailTwFvYVEUpT2_roj_O_ObtN9SB46zVZAplJZr5vZ2c-gEOiiFAZVWEsjEaCwqIwkRgMBTGMGMTkRLqK7n1bNB7Z7RN_KsHXrBfGHaucxUQfqE2u3R75CSJ9DLiY_-jZ4DV0qlGuujqT0JCFtIKp-xFjRWPHnZ18IIUb1ZtX6O8jQm6uu5eNsFAZCCWSsJBSTMGGxTbLGK1lEVU0UjpKbKw51dQIUVOxslQyog3PElwR17jG5TqJZKIoPnYBKoyyBLlf5eK63Xn42eQhIkLITqfVVD877EQOP1_ej5F2kWPEFk6vt-Iv_ckFPsHdrEClIwd2uAol21-DRX8uVI_WQXQml83WaXAedCZuykDQzfOeyj8DxLqBF9QMMcJM9xhlLyimtT5vQHceRtiEcj_v2y0IEMERSxiXMTI7bnhsVMZ4ojjTmYMLVdjy75sOptM0UmeK1JuiCrszE6TFnzRKf_2-_f_tA1hqdO9baavZvtuBZeLaFDDHELEL5fHwze4heBir_cJFAaRz_ii-AcGD1fw
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=PyCIL%3A+A+Python+Toolbox+for+Class-Incremental+Learning&rft.jtitle=arXiv.org&rft.au=Da-Wei%2C+Zhou&rft.au=Fu-Yun%2C+Wang&rft.au=Han-Jia%2C+Ye&rft.au=De-Chuan%2C+Zhan&rft.date=2022-10-26&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422&rft_id=info:doi/10.48550%2Farxiv.2112.12533