Towards Robust Pattern Recognition: A Review

The accuracies for many pattern recognition tasks have increased rapidly year by year, achieving or even outperforming human performance. From the perspective of accuracy, pattern recognition seems to be a nearly solved problem. However, once launched in real applications, the high-accuracy pattern...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the IEEE Vol. 108; no. 6; pp. 894 - 922
Main Authors Zhang, Xu-Yao, Liu, Cheng-Lin, Suen, Ching Y.
Format Journal Article
LanguageEnglish
Published New York IEEE 01.06.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Accuracy
Big Data
Changing environments
Clean and big data
closed world
Distributed control
Human performance
Identification methods
independent and identically distributed
Machine intelligence
Machine learning
Neural networks
Pattern recognition
Pattern recognition systems
robust pattern recognition
Robustness
Task analysis
Task complexity
Online AccessGet full text

Cover

Abstract The accuracies for many pattern recognition tasks have increased rapidly year by year, achieving or even outperforming human performance. From the perspective of accuracy, pattern recognition seems to be a nearly solved problem. However, once launched in real applications, the high-accuracy pattern recognition systems may become unstable and unreliable due to the lack of robustness in open and changing environments. In this article, we present a comprehensive review of research toward robust pattern recognition from the perspective of breaking three basic and implicit assumptions: closed-world assumption, independent and identically distributed assumption, and clean and big data assumption, which form the foundation of most pattern recognition models. Actually, our brain is robust at learning concepts continually and incrementally, in complex, open, and changing environments, with different contexts, modalities, and tasks, by showing only a few examples, under weak or noisy supervision. These are the major differences between human intelligence and machine intelligence, which are closely related to the above three assumptions. After witnessing the significant progress in accuracy improvement nowadays, this review paper will enable us to analyze the shortcomings and limitations of current methods and identify future research directions for robust pattern recognition.
AbstractList The accuracies for many pattern recognition tasks have increased rapidly year by year, achieving or even outperforming human performance. From the perspective of accuracy, pattern recognition seems to be a nearly solved problem. However, once launched in real applications, the high-accuracy pattern recognition systems may become unstable and unreliable due to the lack of robustness in open and changing environments. In this article, we present a comprehensive review of research toward robust pattern recognition from the perspective of breaking three basic and implicit assumptions: closed-world assumption, independent and identically distributed assumption, and clean and big data assumption, which form the foundation of most pattern recognition models. Actually, our brain is robust at learning concepts continually and incrementally, in complex, open, and changing environments, with different contexts, modalities, and tasks, by showing only a few examples, under weak or noisy supervision. These are the major differences between human intelligence and machine intelligence, which are closely related to the above three assumptions. After witnessing the significant progress in accuracy improvement nowadays, this review paper will enable us to analyze the shortcomings and limitations of current methods and identify future research directions for robust pattern recognition.
Author Liu, Cheng-Lin
Suen, Ching Y.
Zhang, Xu-Yao
Author_xml – sequence: 1
  givenname: Xu-Yao
  orcidid: 0000-0001-9260-188X
  surname: Zhang
  fullname: Zhang, Xu-Yao
  email: xyz@nlpr.ia.ac.cn
  organization: National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China
– sequence: 2
  givenname: Cheng-Lin
  orcidid: 0000-0002-6743-4175
  surname: Liu
  fullname: Liu, Cheng-Lin
  email: liucl@nlpr.ia.ac.cn
  organization: National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China
– sequence: 3
  givenname: Ching Y.
  orcidid: 0000-0003-1209-7631
  surname: Suen
  fullname: Suen, Ching Y.
  organization: Centre for Pattern Recognition and Machine Intelligence, Concordia University, Montreal, Canada
BookMark eNp9kE1LAzEQhoNUsK3-Ab0seHVrJtl8eSvFTwotpZ5DdjeRLXVTk9Tiv3driwcPnoYX5nlneAao1_rWInQJeASA1e3LfDGbjAgmeESUVEKSE9QHxmROCOM91McYZK4IqDM0iHGFMaaM0z66WfqdCXXMFr7cxpTNTUo2tNnCVv6tbVLj27ts3MXPxu7O0akz62gvjnOIXh_ul5OnfDp7fJ6Mp3lFFEt5XddCSmoEyLoEsLwojAOggljOKWeElZWRFYWycOAorsAKq6xzRNTUFZwO0fWhdxP8x9bGpFd-G9rupCYFlpwJ0dUNkTxsVcHHGKzTVZPM_uMUTLPWgPXejf5xo_du9NFNh5I_6CY07yZ8_Q9dHaDGWvsLKMCUFop-A5y_cGo
CODEN IEEPAD
CitedBy_id crossref_primary_10_1109_TPAMI_2022_3225117
crossref_primary_10_1016_j_visres_2021_09_004
crossref_primary_10_1109_JPROC_2023_3238024
crossref_primary_10_1016_j_cose_2023_103623
crossref_primary_10_1016_j_visres_2022_108058
crossref_primary_10_1109_ACCESS_2021_3070212
crossref_primary_10_3390_s23031520
crossref_primary_10_1109_TPAMI_2022_3204971
crossref_primary_10_1007_s11424_022_1326_y
crossref_primary_10_1016_j_cortex_2020_12_026
crossref_primary_10_1016_j_jclepro_2023_138911
crossref_primary_10_1007_s11263_023_01972_x
crossref_primary_10_1002_aisy_202200031
crossref_primary_10_1016_j_rineng_2023_101346
crossref_primary_10_1016_j_ijft_2023_100494
crossref_primary_10_1016_j_patcog_2023_109535
crossref_primary_10_1145_3479428
crossref_primary_10_1016_j_patcog_2022_108863
crossref_primary_10_1093_bib_bbad302
crossref_primary_10_1109_TMM_2023_3333659
crossref_primary_10_1109_TIM_2023_3325522
crossref_primary_10_1109_TNNLS_2021_3104392
crossref_primary_10_1016_j_neucom_2024_127666
crossref_primary_10_1007_s11432_021_3502_4
crossref_primary_10_1109_TASE_2022_3215258
crossref_primary_10_1109_TCSVT_2022_3200112
crossref_primary_10_1109_TII_2023_3330340
crossref_primary_10_3390_rs14184551
crossref_primary_10_1016_j_compeleceng_2024_109180
crossref_primary_10_2139_ssrn_5001785
crossref_primary_10_1109_COMST_2023_3338153
crossref_primary_10_1016_j_patcog_2024_110430
crossref_primary_10_1007_s11042_023_17129_4
crossref_primary_10_1109_TII_2022_3179423
crossref_primary_10_3390_ph18010047
crossref_primary_10_1007_s11694_023_02092_3
crossref_primary_10_1016_j_cosrev_2024_100666
crossref_primary_10_1109_TGRS_2023_3293478
crossref_primary_10_1109_ACCESS_2022_3199443
crossref_primary_10_1038_s41598_022_08651_w
crossref_primary_10_1155_2021_4472174
crossref_primary_10_1109_TGRS_2023_3236957
crossref_primary_10_1109_TASLPRO_2025_3543974
crossref_primary_10_11834_jig_230018
crossref_primary_10_1109_ACCESS_2024_3414374
crossref_primary_10_3390_ai5010003
crossref_primary_10_1109_TPAMI_2024_3386985
crossref_primary_10_1109_TGRS_2024_3379669
crossref_primary_10_1049_stg2_12051
crossref_primary_10_3390_rs13214194
crossref_primary_10_1016_j_patcog_2023_109598
crossref_primary_10_1080_00029157_2024_2370777
crossref_primary_10_1016_j_neucom_2022_05_023
crossref_primary_10_1142_S0218001424510212
crossref_primary_10_1016_j_neucom_2022_12_011
crossref_primary_10_1016_j_biosystems_2025_105410
crossref_primary_10_1109_TPAMI_2020_3045079
crossref_primary_10_3390_app13042293
crossref_primary_10_1109_ACCESS_2024_3494885
crossref_primary_10_1016_j_patcog_2022_108889
crossref_primary_10_1007_s13721_024_00450_9
crossref_primary_10_1016_j_engappai_2024_109290
crossref_primary_10_1016_j_patcog_2024_110283
crossref_primary_10_1016_j_ins_2025_121940
crossref_primary_10_1016_j_procs_2022_11_097
Cites_doi 10.1016/j.sigpro.2013.12.026
10.1016/j.neuroimage.2011.09.069
10.24963/ijcai.2018/278
10.1109/ICCV.2017.328
10.1145/1553374.1553534
10.1109/TGRS.2013.2286827
10.1109/TPAMI.1979.4766902
10.1109/5.18626
10.1023/B:AIRE.0000045502.10941.a9
10.1109/SP.2017.49
10.1109/CVPR.2018.00750
10.1109/TPAMI.2018.2858759
10.1109/TPAMI.2014.2353635
10.1109/MSP.2017.2738401
10.1109/3477.809043
10.1109/TPAMI.2012.239
10.1109/TPAMI.2016.2646371
10.1109/TPAMI.2003.1251144
10.1109/TPAMI.2017.2762295
10.1109/TNN.2010.2091281
10.1109/72.914517
10.1109/TPAMI.2008.137
10.1109/TPAMI.2014.2321392
10.1006/csla.1995.0010
10.1007/978-3-319-46493-0_35
10.1109/CVPR.2011.5995664
10.1109/TPAMI.2007.250598
10.1016/S0031-3203(03)00085-2
10.1109/CVPR.2018.00391
10.1109/CVPR.2018.00362
10.1109/TPAMI.2016.2577031
10.1016/j.neucom.2018.05.083
10.1109/TPAMI.2007.1037
10.5244/C.31.42
10.1109/TPAMI.2017.2773081
10.1109/TPAMI.2012.274
10.1109/CVPR.2018.00456
10.1109/ICDM.2016.0121
10.1016/j.patcog.2004.05.013
10.1109/TPAMI.2016.2613924
10.18653/v1/D17-1314
10.1109/CVPR.2017.126
10.1109/CVPR.2018.00451
10.1007/3-540-47977-5_56
10.1109/CVPR.2018.00915
10.1016/j.neunet.2014.09.003
10.1109/CVPR.2018.00781
10.1162/089976600300015349
10.1109/CVPR.2017.76
10.1109/ICCV.2017.88
10.1109/PROC.1968.6414
10.1038/nature14539
10.1109/SP.2016.41
10.1109/CVPR.2017.74
10.1016/j.neuron.2016.10.050
10.1109/CVPR.2018.00575
10.1109/TKDE.2009.191
10.1109/CVPR.1991.139730
10.1109/CVPR.2016.278
10.1198/016214507000000617
10.1109/CVPR.2019.00202
10.1007/s11263-012-0594-8
10.1109/TPAMI.2015.2496141
10.1109/CVPR.2018.00450
10.1016/j.artint.2013.06.003
10.1109/CVPR.2018.00879
10.1109/ICCV.2015.320
10.1109/CVPR.2018.00131
10.1109/TPAMI.2013.83
10.1109/TPAMI.2017.2737007
10.1109/CVPR.2015.7298799
10.1109/TPAMI.2003.1240120
10.1162/neco.1995.7.1.108
10.1007/s10994-016-5610-8
10.1109/TKDE.2005.186
10.1162/089976601750264965
10.1109/TPAMI.2019.2899857
10.1109/TPAMI.2006.248
10.1109/ICCV.2015.134
10.1109/ICCV.2017.226
10.1109/TPAMI.2015.2500224
10.1109/TPAMI.2005.19
10.1016/j.neunet.2019.01.012
10.1016/j.patcog.2018.01.025
10.1007/978-3-319-46466-4_37
10.1126/science.1127647
10.1109/CVPR.2016.643
10.1201/9781315139470
10.1109/TPAMI.2015.2487986
10.1609/aimag.v38i3.2756
10.1109/CVPR.2018.00581
10.1142/0580
10.1109/TPAMI.2009.167
10.1109/TIP.2014.2329449
10.1287/opre.1100.0854
10.3115/v1/P15-2139
10.1109/ICCV.2017.73
10.7551/mitpress/9780262033589.001.0001
10.1109/TPAMI.2018.2798607
10.1109/TPAMI.2016.2615921
10.1016/j.patcog.2016.08.005
10.1145/3191513
10.1109/TPAMI.2016.2535231
10.1145/1390156.1390294
10.1109/34.142911
10.1109/TPAMI.2005.18
10.1023/B:MACH.0000008084.60811.49
10.1145/3052973.3053009
10.1109/CVPR.2015.7298965
10.1145/1541880.1541882
10.1109/CVPR.2018.00111
10.1109/CVPR.2018.00571
10.1162/NECO_a_00155
10.1109/ICCV.2015.430
10.1007/BF00994018
10.1017/S026988890999035X
10.1109/TPAMI.2013.140
10.1109/CVPR.2016.285
10.2307/2289860
10.1109/CVPR.2016.556
10.1109/TPAMI.2007.56
10.1016/j.patcog.2010.11.015
10.1109/CVPR.2013.431
10.1016/0031-3203(93)90097-G
10.1145/1015330.1015422
10.1109/79.536825
10.1109/TPAMI.2007.1030
10.1109/EuroSP.2016.36
10.1109/TPAMI.2014.2307881
10.1109/TPAMI.2016.2587647
10.1016/j.compmedimag.2014.11.010
10.1023/A:1022699900025
10.1016/S0004-3702(96)00034-3
10.1109/ICCV.2015.11
10.1613/jair.606
10.1109/CVPR.2015.7298594
10.1109/CVPR.2017.240
10.1613/jair.1872
10.1109/CVPR.2018.00582
10.1109/ICRA.2016.7487708
10.1016/j.patcog.2010.05.010
10.1109/CVPR.2017.17
10.1007/978-3-319-46487-9_40
10.1109/CVPR.2017.316
10.1145/279943.279962
10.1109/CVPR.2018.00429
10.1007/978-3-319-46466-4_5
10.1109/CVPR.2018.00610
10.1109/CVPR.2016.485
10.1109/TPAMI.2006.79
10.1016/j.patrec.2008.03.010
10.1109/CVPR.2017.587
10.1109/TPAMI.2011.52
10.1007/s11263-013-0693-1
10.1109/TPAMI.2018.2858821
10.1109/ICPR.2010.813
10.1109/TPAMI.2018.2849989
10.1109/TPAMI.2010.109
10.1561/0600000027
10.1109/CVPR.2016.247
10.1109/ICCV.2015.463
10.1109/TPAMI.2018.2814042
10.1109/TPAMI.2017.2739147
10.1109/TKDE.2010.61
10.1109/TITS.2016.2598356
10.1109/CVPR.2016.173
10.1109/TPAMI.2013.50
10.1109/CVPR.2016.90
10.1109/TIT.1970.1054406
10.1126/science.aab3050
10.1109/TPAMI.2015.2461544
10.1109/TPAMI.2008.240
10.1016/j.ins.2017.11.061
10.1109/CVPR.2016.282
10.1007/978-94-015-8630-6
10.1109/TPAMI.2018.2857768
10.1016/S0378-3758(00)00115-4
10.1007/s100320200076
10.1023/A:1007601015854
10.1109/TPAMI.1983.4767411
10.1002/0471660264
10.1109/MSP.2017.2740965
10.1109/CVPR.2015.7298640
10.1109/TPAMI.2015.2456899
10.1109/TNN.2008.2005605
10.1109/34.273716
10.1109/5.726791
10.1109/TMM.2015.2477044
10.1109/CVPR.2018.00363
10.1142/p191
10.1109/34.824819
10.1109/TPAMI.2017.2723882
10.1109/TPAMI.2012.256
10.1147/JRD.2017.2701178
10.1109/TPAMI.2011.283
10.1016/j.neucom.2014.09.081
10.1109/CVPR.2018.00760
10.1109/CVPR.2018.00417
10.1109/TASL.2011.2134090
10.1109/TPAMI.2011.264
10.1145/1390156.1390177
10.1109/CVPR.2018.00366
10.1145/3133944.3133949
10.1109/CVPR.2018.00950
10.1023/A:1007379606734
10.1109/TNNLS.2013.2292894
10.1016/j.patrec.2009.09.011
10.1109/CVPR.2018.00906
10.1109/CVPR.2014.220
10.1109/CVPR.2019.01158
10.1007/978-3-642-33709-3_50
10.1561/0600000033
10.1109/TPAMI.2015.2505293
10.1109/CVPR.2018.00393
10.1109/TNNLS.2016.2637351
10.1145/1143844.1143891
10.1109/ICCV.2015.167
10.1109/CVPR.2016.433
10.1109/CVPR.2005.283
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
DOI 10.1109/JPROC.2020.2989782
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
Electronics & Communications Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList
Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-2256
EndPage 922
ExternalDocumentID 10_1109_JPROC_2020_2989782
9103349
Genre orig-research
GrantInformation_xml – fundername: Key Research Program of Frontier Sciences of the Chinese Academy of Sciences (CAS)
  grantid: ZDBS-LY-7004
  funderid: 10.13039/501100002367
– fundername: National Natural Science Foundation of China (NSFC)
  grantid: 61633021; 61721004
  funderid: 10.13039/501100001809
– fundername: Youth Innovation Promotion Association of CAS
  grantid: 2019141
  funderid: 10.13039/501100002367
– fundername: Young Elite Scientists Sponsorship Program of the China Association for Science and Technology (CAST)
  grantid: 2018QNRC001
  funderid: 10.13039/100010097
– fundername: Major Project for New Generation of AI
  grantid: 2018AAA0100400
GroupedDBID -DZ
-~X
.DC
0R~
123
1OL
29P
3EH
4.4
6IK
85S
97E
9M8
AAJGR
AAWTH
ABAZT
ABFSI
ABJNI
ABQJQ
ABVLG
ACBEA
ACGFS
AENEX
AETEA
AETIX
AFOGA
AGNAY
AGQYO
AGSQL
AHBIQ
AIBXA
ALLEH
ALMA_UNASSIGNED_HOLDINGS
AZLTO
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
FA8
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MVM
O9-
OCL
RIA
RIE
RIU
RNS
TAE
TN5
TWZ
UDY
UHB
UKR
UQL
VOH
WHG
XJT
XOL
YNT
ZCA
ZXP
ZY4
~02
AAYOK
AAYXX
CITATION
RIG
7SP
8FD
L7M
ID FETCH-LOGICAL-c295t-ddd7883a718db11e644af11372e6636525bca8c31b4f1f30c1e7e9eff27d3f463
IEDL.DBID RIE
ISSN 0018-9219
IngestDate Fri Jul 25 07:50:37 EDT 2025
Tue Jul 01 03:52:56 EDT 2025
Thu Apr 24 23:01:50 EDT 2025
Wed Aug 27 02:38:34 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 6
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-c295t-ddd7883a718db11e644af11372e6636525bca8c31b4f1f30c1e7e9eff27d3f463
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-1209-7631
0000-0001-9260-188X
0000-0002-6743-4175
PQID 2408657711
PQPubID 85453
PageCount 29
ParticipantIDs proquest_journals_2408657711
crossref_primary_10_1109_JPROC_2020_2989782
crossref_citationtrail_10_1109_JPROC_2020_2989782
ieee_primary_9103349
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2020-06-01
PublicationDateYYYYMMDD 2020-06-01
PublicationDate_xml – month: 06
  year: 2020
  text: 2020-06-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle Proceedings of the IEEE
PublicationTitleAbbrev JPROC
PublicationYear 2020
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
ref207
ref56
ref329
ref208
ref205
ref58
ref327
ref206
ref325
ref204
ref55
ref322
ref201
ref323
ref202
ref209
ciliberto (ref45) 2017
han (ref101) 2016
ref210
ref332
ref211
ref50
ref330
vinyals (ref292) 2016
ref46
zhao (ref331) 2016
ref218
szegedy (ref269) 2014
ref219
ref48
ref337
ref216
ref47
ref217
ref42
ref214
ref41
ref336
ref333
ref212
ref43
grandvalet (ref90) 2009
ref213
zhou (ref335) 2018
ref49
kingma (ref139) 2014
ref8
ref7
masnadi-shirazi (ref183) 2009
ref9
smola (ref255) 2007
ref4
jiang (ref126) 2018
ref3
ref6
ref221
ref340
zhu (ref338) 2006
ref341
ref220
ref35
ref306
ref34
ref37
ref304
ref36
ref305
ref31
ref302
ref30
ref303
ref33
ref300
ref32
ref301
radford (ref222) 2018
li (ref162) 2019
ref39
ref38
kamnitsas (ref130) 2018
ref308
kingma (ref140) 2013
salimans (ref238) 2016
springenberg (ref257) 2016
huang (ref118) 2007
xu (ref310) 2006
rasmus (ref224) 2015
dai (ref51) 2015
liu (ref166) 2014
tarvainen (ref272) 2017
ref24
ref23
ref318
ref26
ref25
dai (ref52) 2017
ref316
sutskever (ref267) 2014
ref313
ref314
murugesan (ref196) 2016
ref311
ref21
ref312
goodfellow (ref86) 2016
zhang (ref328) 2016
ref28
ref27
ref29
reed (ref229) 2016
srivastava (ref258) 2014; 15
ref320
ref200
zhou (ref334) 2004
ravi (ref226) 2017
goodfellow (ref87) 2014
ref128
ref249
ref247
molnar (ref191) 2019
ref127
ref248
ref99
ref124
ref245
ref98
ref125
ref246
gu (ref95) 2014
maas (ref179) 2013
zhang (ref324) 2010; 11
finn (ref70) 2017
liu (ref171) 2018
ref133
ref254
ref92
ref134
ref131
ref252
ref94
ref132
ref253
ref251
ref91
ref137
ref135
ref136
(ref122) 0
triantafillou (ref279) 2017
ref82
ref144
ganin (ref79) 2015
ref145
ref266
ref142
ref264
ref261
ref80
ref108
ref227
hendrycks (ref109) 2017
ref107
vahdat (ref285) 2017
ref225
ref104
srivastava (ref259) 2012
ref74
ref77
ref223
ref102
ref103
huang (ref119) 2010
glorot (ref84) 2010
samangouei (ref239) 2018
ref71
ref232
ref111
ref112
ref72
ref231
gönen (ref85) 2011; 12
ref68
ref67
goodfellow (ref88) 2015
ref117
ref69
ref64
ref116
ref66
ref234
ref113
ref65
ref235
ref114
freund (ref73) 1996
shaham (ref250) 2015
grandvalet (ref89) 2005
chowdhuri (ref44) 2017
tax (ref273) 2001
kingma (ref138) 2015
santoro (ref241) 2017
ref60
ref243
ref244
thrun (ref277) 1996
ref62
ref120
ref61
ref242
ref121
bishop (ref20) 2006
ref240
han (ref100) 2018
bertinetto (ref16) 2016
bautista (ref10) 2016
ref168
sun (ref265) 2009; 31
ref169
krizhevsky (ref146) 2012
ref290
ref170
ref291
hinton (ref110) 2006; 313
gidaris (ref83) 2018
he (ref106) 2019
ref177
ref298
ref178
ref299
ref296
ref176
ref297
ref173
ref294
ref174
ref295
darrell (ref53) 2015; 5
ref172
ref293
yosinski (ref315) 2014
sajjadi (ref237) 2016
devlin (ref54) 2018
bengio (ref14) 2003; 3
sukhbaatar (ref263) 2015
kurakin (ref148) 2016
ref181
donahue (ref59) 2014
pentina (ref215) 2015
ref188
koller (ref143) 2009
ref189
ref187
ref184
ref185
zhang (ref326) 2011
frome (ref75) 2013
ref149
ref268
ref147
rifai (ref233) 2011
laskov (ref156) 2006; 7
motiian (ref194) 2017
ref276
ref155
ref274
ref153
fukunaga (ref78) 1990
ref275
ref154
ref152
ref270
ref271
ref150
laine (ref151) 2017
ref278
xu (ref309) 2015
ghosh (ref81) 2017
ref158
bengio (ref15) 2015
he (ref105) 2018
ioffe (ref123) 2015
lee (ref159) 2013
kipf (ref141) 2017
ref287
bilen (ref17) 2016
ref288
ref167
ref164
sugiyama (ref262) 2008
ref283
oliver (ref203) 2018
ref284
ref163
zhang (ref321) 2017
ref281
ref160
ref282
ref161
ref13
ref12
zhang (ref317) 2017
xiao (ref307) 2015
ref11
metzen (ref186) 2017
ref19
reed (ref230) 2015
ruder (ref236) 2017
guyon (ref97) 2003; 3
vapnik (ref286) 1998
long (ref175) 2015
chen (ref40) 2018
lecun (ref157) 2015; 521
ref2
ref1
snell (ref256) 2017
ref192
ref190
mansour (ref182) 2009
zhu (ref339) 2003
ref199
li (ref165) 2018
nagy (ref198) 1968; 56
bojanowski (ref22) 2017
andrew (ref5) 2013
ref197
fu (ref76) 1980; 29
ref195
ref193
velickovic (ref289) 2018
malmaud (ref180) 2015
su (ref260) 2017
guerriero (ref96) 2018
tsochantaridis (ref280) 2005; 6
kaiser (ref129) 2017
hoffman (ref115) 2013
duda (ref63) 2001
bishop (ref18) 1995
recht (ref228) 2018
zhang (ref319) 2018
gretton (ref93) 2007
References_xml – ident: ref216
  doi: 10.1016/j.sigpro.2013.12.026
– year: 2015
  ident: ref15
  article-title: Towards biologically plausible deep learning
  publication-title: arXiv 1502 04156
– start-page: 833
  year: 2011
  ident: ref233
  article-title: Contractive auto-encoders: Explicit invariance during feature extraction
  publication-title: Proc Int Conf Mach Learn
– volume: 3
  start-page: 1157
  year: 2003
  ident: ref97
  article-title: An introduction to variable and feature selection
  publication-title: J Mach Learn Res
– ident: ref318
  doi: 10.1016/j.neuroimage.2011.09.069
– start-page: 2234
  year: 2016
  ident: ref238
  article-title: Improved techniques for training GANs
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref37
  doi: 10.24963/ijcai.2018/278
– ident: ref103
  doi: 10.1109/ICCV.2017.328
– start-page: 1247
  year: 2013
  ident: ref5
  article-title: Deep canonical correlation analysis
  publication-title: Proc Int Conf Mach Learn
– ident: ref337
  doi: 10.1145/1553374.1553534
– start-page: 3846
  year: 2016
  ident: ref10
  article-title: CliqueCNN: Deep unsupervised exemplar learning
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref133
  doi: 10.1109/TGRS.2013.2286827
– year: 2019
  ident: ref191
  publication-title: Interpretable Machine Learning A Guide for Making Black Box Models Explainable
– year: 2017
  ident: ref236
  article-title: An overview of multi-task learning in deep neural networks
  publication-title: ArXiv 1706 05098
– year: 2015
  ident: ref250
  article-title: Understanding adversarial training: Increasing local stability of neural nets through robust optimization
  publication-title: arXiv 1511 05432
– start-page: 523
  year: 2016
  ident: ref16
  article-title: Learning feed-forward one-shot learners
  publication-title: Proc Adv Neural Inf Process Syst
– start-page: 1
  year: 2018
  ident: ref130
  article-title: Semi-supervised learning via compact latent space clustering
  publication-title: Proc Int Conf Mach Learn
– ident: ref261
  doi: 10.1109/TPAMI.1979.4766902
– ident: ref221
  doi: 10.1109/5.18626
– ident: ref112
  doi: 10.1023/B:AIRE.0000045502.10941.a9
– start-page: 1180
  year: 2015
  ident: ref79
  article-title: Unsupervised domain adaptation by backpropagation
  publication-title: Proc Int Conf Mach Learn
– start-page: 2222
  year: 2012
  ident: ref259
  article-title: Multimodal learning with deep Boltzmann machines
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref31
  doi: 10.1109/SP.2017.49
– ident: ref94
  doi: 10.1109/CVPR.2018.00750
– start-page: 321
  year: 2004
  ident: ref334
  article-title: Learning with local and global consistency
  publication-title: Proc Adv Neural Inf Process Syst
– year: 2019
  ident: ref106
  article-title: Momentum contrast for unsupervised visual representation learning
  publication-title: arXiv 1911 05722
– ident: ref333
  doi: 10.1109/TPAMI.2018.2858759
– ident: ref104
  doi: 10.1109/TPAMI.2014.2353635
– start-page: 1195
  year: 2017
  ident: ref272
  article-title: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref223
  doi: 10.1109/MSP.2017.2738401
– year: 1990
  ident: ref78
  publication-title: Introduction to statistical pattern recognition
– ident: ref41
  doi: 10.1109/3477.809043
– ident: ref327
  doi: 10.1109/TPAMI.2012.239
– ident: ref252
  doi: 10.1109/TPAMI.2016.2646371
– volume: 12
  start-page: 2211
  year: 2011
  ident: ref85
  article-title: Multiple kernel learning algorithms
  publication-title: J Mach Learn Res
– ident: ref296
  doi: 10.1109/TPAMI.2003.1251144
– start-page: 1
  year: 2015
  ident: ref175
  article-title: Learning transferable features with deep adaptation networks
  publication-title: Proc Int Conf Mach Learn
– ident: ref176
  doi: 10.1109/TPAMI.2017.2762295
– ident: ref205
  doi: 10.1109/TNN.2010.2091281
– ident: ref195
  doi: 10.1109/72.914517
– ident: ref92
  doi: 10.1109/TPAMI.2008.137
– ident: ref245
  doi: 10.1109/TPAMI.2014.2321392
– ident: ref161
  doi: 10.1006/csla.1995.0010
– ident: ref155
  doi: 10.1007/978-3-319-46493-0_35
– ident: ref65
  doi: 10.1109/CVPR.2011.5995664
– start-page: 1
  year: 2017
  ident: ref141
  article-title: Semi-supervised classification with graph convolutional networks
  publication-title: Proc Int Conf Learn Represent
– ident: ref312
  doi: 10.1109/TPAMI.2007.250598
– year: 2018
  ident: ref335
  article-title: Graph neural networks: A review of methods and applications
  publication-title: arXiv 1812 08434
– ident: ref169
  doi: 10.1016/S0031-3203(03)00085-2
– ident: ref316
  doi: 10.1109/CVPR.2018.00391
– start-page: 1
  year: 2013
  ident: ref159
  article-title: Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks
  publication-title: Proc Int Machine Learning Workshop
– start-page: 2121
  year: 2013
  ident: ref75
  article-title: DeViSE: A deep visual-semantic embedding model
  publication-title: Proc Adv Neural Inf Process Syst
– start-page: 1041
  year: 2009
  ident: ref182
  article-title: Domain adaptation with multiple sources
  publication-title: Proc Adv Neural Inf Process Syst
– start-page: 1919
  year: 2017
  ident: ref81
  article-title: Robust loss functions under label noise for deep neural networks
  publication-title: Proc AAAI Conf Artif Intell
– ident: ref329
  doi: 10.1109/CVPR.2018.00362
– ident: ref231
  doi: 10.1109/TPAMI.2016.2577031
– volume: 11
  start-page: 1081
  year: 2010
  ident: ref324
  article-title: Analysis of multi-stage convex relaxation for sparse regularization
  publication-title: J Mach Learn Res
– ident: ref297
  doi: 10.1016/j.neucom.2018.05.083
– volume: 5
  start-page: 18
  year: 2015
  ident: ref53
  article-title: Machine learning with interdependent and non-identically distributed data
  publication-title: Dagstuhl report
– ident: ref137
  doi: 10.1109/TPAMI.2007.1037
– ident: ref80
  doi: 10.5244/C.31.42
– ident: ref164
  doi: 10.1109/TPAMI.2017.2773081
– year: 2017
  ident: ref44
  article-title: MultiNet: Multi-modal multi-task learning for autonomous driving
  publication-title: arXiv 1709 05581
– ident: ref330
  doi: 10.1109/TPAMI.2012.274
– ident: ref234
  doi: 10.1109/CVPR.2018.00456
– volume: 29
  start-page: 845
  year: 1980
  ident: ref76
  article-title: Recent developments in pattern recognition
  publication-title: IEEE Trans Comput
– ident: ref127
  doi: 10.1109/ICDM.2016.0121
– ident: ref167
  doi: 10.1016/j.patcog.2004.05.013
– ident: ref320
  doi: 10.1109/TPAMI.2016.2613924
– start-page: 529
  year: 2005
  ident: ref89
  article-title: Semi-supervised learning by entropy minimization
  publication-title: Proc Adv Neural Inf Process Syst
– start-page: 3235
  year: 2018
  ident: ref203
  article-title: Realistic evaluation of deep semi-supervised learning algorithms
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref254
  doi: 10.18653/v1/D17-1314
– start-page: 6510
  year: 2017
  ident: ref52
  article-title: Good semi-supervised learning that requires a bad GAN
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref178
  doi: 10.1109/CVPR.2017.126
– ident: ref30
  doi: 10.1109/CVPR.2018.00451
– start-page: 5596
  year: 2017
  ident: ref285
  article-title: Toward robustness against label noise in training deep discriminative neural networks
  publication-title: Proc Adv Neural Inf Process Syst
– volume: 7
  start-page: 1909
  year: 2006
  ident: ref156
  article-title: Incremental support vector learning: Analysis, implementation and applications
  publication-title: J Mach Learn Res
– ident: ref251
  doi: 10.1007/3-540-47977-5_56
– ident: ref211
  doi: 10.1109/CVPR.2018.00915
– ident: ref247
  doi: 10.1016/j.neunet.2014.09.003
– ident: ref135
  doi: 10.1109/CVPR.2018.00781
– ident: ref276
  doi: 10.1162/089976600300015349
– ident: ref323
  doi: 10.1109/CVPR.2017.76
– ident: ref28
  doi: 10.1109/ICCV.2017.88
– volume: 6
  start-page: 1453
  year: 2005
  ident: ref280
  article-title: Large margin methods for structured and interdependent output variables
  publication-title: J Mach Learn Res
– start-page: 920
  year: 2003
  ident: ref339
  article-title: Eliminating class noise in large datasets
  publication-title: Proc Int Conf Mach Learn
– start-page: 1
  year: 2018
  ident: ref289
  article-title: Graph attention networks
  publication-title: Proc Int Conf Learn Represent
– volume: 56
  start-page: 836
  year: 1968
  ident: ref198
  article-title: state of the art in pattern recognition
  publication-title: Proceedings of the IEEE
  doi: 10.1109/PROC.1968.6414
– start-page: 513
  year: 2007
  ident: ref93
  article-title: A kernel method for the two-sample-problem
  publication-title: Proc Adv Neural Inf Process Syst
– volume: 521
  start-page: 436
  year: 2015
  ident: ref157
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– ident: ref209
  doi: 10.1109/SP.2016.41
– ident: ref98
  doi: 10.1109/CVPR.2017.74
– start-page: 1
  year: 2010
  ident: ref119
  article-title: Robust metric learning by smooth optimization
  publication-title: Proc Conf Uncertain Artif Intell
– ident: ref217
  doi: 10.1016/j.neuron.2016.10.050
– ident: ref278
  doi: 10.1109/CVPR.2018.00575
– ident: ref206
  doi: 10.1109/TKDE.2009.191
– start-page: 2672
  year: 2014
  ident: ref87
  article-title: Generative adversarial nets
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref35
  doi: 10.1109/CVPR.1991.139730
– ident: ref212
  doi: 10.1109/CVPR.2016.278
– ident: ref303
  doi: 10.1198/016214507000000617
– start-page: 1
  year: 2017
  ident: ref186
  article-title: On detecting adversarial perturbations
  publication-title: Proc Int Conf Learn Represent
– ident: ref142
  doi: 10.1109/CVPR.2019.00202
– ident: ref295
  doi: 10.1007/s11263-012-0594-8
– ident: ref61
  doi: 10.1109/TPAMI.2015.2496141
– start-page: 1
  year: 2017
  ident: ref151
  article-title: Temporal ensembling for semi-supervised learning
  publication-title: Proc Int Conf Learn Represent
– start-page: 2048
  year: 2015
  ident: ref309
  article-title: Show, attend and tell: Neural image caption generation with visual attention
  publication-title: Proc Int Conf Mach Learn
– ident: ref290
  doi: 10.1109/CVPR.2018.00450
– ident: ref4
  doi: 10.1016/j.artint.2013.06.003
– start-page: 249
  year: 2010
  ident: ref84
  article-title: Understanding the difficulty of training deep feedforward neural networks
  publication-title: Proc Int Conf Artif Intell Stat
– start-page: 1433
  year: 2008
  ident: ref262
  article-title: Direct importance estimation with model selection and its application to covariate shift adaptation
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref197
  doi: 10.1109/CVPR.2018.00879
– start-page: 1
  year: 2014
  ident: ref269
  article-title: Intriguing properties of neural networks
  publication-title: Proc Int Conf Learn Represent
– ident: ref299
  doi: 10.1109/ICCV.2015.320
– ident: ref266
  doi: 10.1109/CVPR.2018.00131
– start-page: 3
  year: 2013
  ident: ref179
  article-title: Rectifier nonlinearities improve neural network acoustic models
  publication-title: Proc Int Conf Mach Learn
– start-page: 1
  year: 2016
  ident: ref101
  article-title: Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding
  publication-title: Proc Int Conf Learn Represent
– ident: ref185
  doi: 10.1109/TPAMI.2013.83
– ident: ref77
  doi: 10.1109/TPAMI.2017.2737007
– ident: ref11
  doi: 10.1109/CVPR.2015.7298799
– start-page: 1
  year: 2016
  ident: ref257
  article-title: Unsupervised and semi-supervised learning with categorical generative adversarial networks
  publication-title: Proc Int Conf Learn Represent
– start-page: 1
  year: 2015
  ident: ref123
  article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift
  publication-title: Proc Int Conf Mach Learn
– ident: ref187
  doi: 10.1109/TPAMI.2003.1240120
– year: 2006
  ident: ref20
  publication-title: Pattern Recognition and Machine Learning
– year: 2017
  ident: ref129
  article-title: One model to learn them all
  publication-title: arXiv 1706 05137
– year: 2006
  ident: ref338
  article-title: Semi-supervised learning literature survey
– ident: ref19
  doi: 10.1162/neco.1995.7.1.108
– ident: ref128
  doi: 10.1007/s10994-016-5610-8
– ident: ref336
  doi: 10.1109/TKDE.2005.186
– year: 2018
  ident: ref222
  article-title: Improving language understanding by generative pre-training
– ident: ref248
  doi: 10.1162/089976601750264965
– ident: ref173
  doi: 10.1109/TPAMI.2019.2899857
– ident: ref39
  doi: 10.1109/TPAMI.2006.248
– ident: ref294
  doi: 10.1109/ICCV.2015.134
– ident: ref58
  doi: 10.1109/ICCV.2017.226
– ident: ref8
  doi: 10.1109/TPAMI.2015.2500224
– year: 2014
  ident: ref95
  article-title: Towards deep neural network architectures robust to adversarial examples
  publication-title: arXiv 1412 5068 [cs]
– start-page: 4080
  year: 2017
  ident: ref256
  article-title: Prototypical networks for few-shot learning
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref287
  doi: 10.1109/TPAMI.2005.19
– ident: ref210
  doi: 10.1016/j.neunet.2019.01.012
– ident: ref116
  doi: 10.1016/j.patcog.2018.01.025
– year: 2015
  ident: ref180
  article-title: What's Cookin'? Interpreting cooking videos using text, speech and vision
  publication-title: arXiv 1503 01558
– start-page: 148
  year: 1996
  ident: ref73
  article-title: Experiments with a new boosting algorithm
  publication-title: Proc Int Conf Mach Learn
– start-page: 3104
  year: 2014
  ident: ref267
  article-title: Sequence to sequence learning with neural networks
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref302
  doi: 10.1007/978-3-319-46466-4_37
– start-page: 3630
  year: 2016
  ident: ref292
  article-title: Matching networks for one shot learning
  publication-title: Proc Adv Neural Inf Process Syst
– volume: 313
  start-page: 504
  year: 2006
  ident: ref110
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
  doi: 10.1126/science.1127647
– start-page: 1
  year: 2015
  ident: ref88
  article-title: Explaining and harnessing adversarial examples
  publication-title: Proc Int Conf Learn Represent
– start-page: 1
  year: 2013
  ident: ref115
  article-title: Efficient learning of domain-invariant image representations
  publication-title: Proc Int Conf Learn Represent
– ident: ref2
  doi: 10.1109/CVPR.2016.643
– ident: ref23
  doi: 10.1201/9781315139470
– start-page: 1
  year: 2015
  ident: ref263
  article-title: Training convolutional networks with noisy labels
  publication-title: Proc Workshop Int Conf Learn Represent
– ident: ref1
  doi: 10.1109/TPAMI.2015.2487986
– ident: ref55
  doi: 10.1609/aimag.v38i3.2756
– ident: ref306
  doi: 10.1109/CVPR.2018.00581
– start-page: 2691
  year: 2015
  ident: ref307
  article-title: Learning from massive noisy labeled data for image classification
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit
– ident: ref27
  doi: 10.1142/0580
– ident: ref69
  doi: 10.1109/TPAMI.2009.167
– ident: ref60
  doi: 10.1109/TIP.2014.2329449
– year: 1998
  ident: ref286
  publication-title: Statistical Learning Theory
– ident: ref25
  doi: 10.1287/opre.1100.0854
– year: 2018
  ident: ref100
  article-title: Masking: A new perspective of noisy supervision
  publication-title: arXiv 1805 08193
– ident: ref64
  doi: 10.3115/v1/P15-2139
– ident: ref7
  doi: 10.1109/ICCV.2017.73
– start-page: 2309
  year: 2018
  ident: ref126
  article-title: MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels
  publication-title: Proc Int Conf Mach Learn
– start-page: 1
  year: 2015
  ident: ref138
  article-title: Adam: A method for stochastic optimization
  publication-title: Proc Int Conf Learn Represent
– ident: ref36
  doi: 10.7551/mitpress/9780262033589.001.0001
– start-page: 1
  year: 2018
  ident: ref40
  article-title: GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks
  publication-title: Proc Int Conf Mach Learn
– ident: ref9
  doi: 10.1109/TPAMI.2018.2798607
– start-page: 1
  year: 2018
  ident: ref319
  article-title: Mixup: Beyond empirical risk minimization
  publication-title: Proc Int Conf Learn Represent
– year: 2018
  ident: ref171
  article-title: Learn to combine modalities in multimodal deep learning
  publication-title: arXiv 1805 11730
– start-page: 3581
  year: 2014
  ident: ref139
  article-title: Semi-supervised learning with deep generative models
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref49
  doi: 10.1109/TPAMI.2016.2615921
– ident: ref325
  doi: 10.1016/j.patcog.2016.08.005
– ident: ref189
  doi: 10.1145/3191513
– start-page: 1126
  year: 2017
  ident: ref70
  article-title: Model-agnostic meta-learning for fast adaptation of deep networks
  publication-title: Proc Int Conf Mach Learn
– start-page: 1060
  year: 2016
  ident: ref229
  article-title: Generative adversarial text to image synthesis
  publication-title: Proc Int Conf Mach Learn
– ident: ref46
  doi: 10.1109/TPAMI.2016.2535231
– ident: ref291
  doi: 10.1145/1390156.1390294
– ident: ref99
  doi: 10.1109/34.142911
– start-page: 3546
  year: 2015
  ident: ref224
  article-title: Semi-supervised learning with ladder networks
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref243
  doi: 10.1109/TPAMI.2005.18
– start-page: 601
  year: 2007
  ident: ref118
  article-title: Correcting sample selection bias by unlabeled data
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref274
  doi: 10.1023/B:MACH.0000008084.60811.49
– ident: ref207
  doi: 10.1145/3052973.3053009
– ident: ref174
  doi: 10.1109/CVPR.2015.7298965
– ident: ref34
  doi: 10.1145/1541880.1541882
– ident: ref340
  doi: 10.1109/CVPR.2018.00111
– ident: ref160
  doi: 10.1109/CVPR.2018.00571
– ident: ref108
  doi: 10.1162/NECO_a_00155
– year: 2009
  ident: ref143
  publication-title: Probabilistic Graphical Models
– ident: ref3
  doi: 10.1109/ICCV.2015.430
– ident: ref48
  doi: 10.1007/BF00994018
– ident: ref71
  doi: 10.1017/S026988890999035X
– ident: ref154
  doi: 10.1109/TPAMI.2013.140
– ident: ref225
  doi: 10.1109/CVPR.2016.285
– start-page: 1097
  year: 2012
  ident: ref146
  article-title: ImageNet classification with deep convolutional neural networks
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref74
  doi: 10.2307/2289860
– ident: ref314
  doi: 10.1109/CVPR.2016.556
– start-page: 537
  year: 2009
  ident: ref90
  article-title: Support vector machines with a reject option
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref249
  doi: 10.1109/TPAMI.2007.56
– ident: ref26
  doi: 10.1016/j.patcog.2010.11.015
– ident: ref149
  doi: 10.1109/CVPR.2013.431
– year: 0
  ident: ref122
  publication-title: Imagenet Large Scale Visual Recognition Challenge
– ident: ref62
  doi: 10.1016/0031-3203(93)90097-G
– start-page: 647
  year: 2014
  ident: ref59
  article-title: DeCAF: A deep convolutional activation feature for generic visual recognition
  publication-title: Proc Int Conf Mach Learn
– start-page: 1163
  year: 2016
  ident: ref237
  article-title: Regularization with stochastic transformations and perturbations for deep semi-supervised learning
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref150
  doi: 10.1145/1015330.1015422
– ident: ref181
  doi: 10.1109/79.536825
– start-page: 13
  year: 2007
  ident: ref255
  article-title: A Hilbert space embedding for distributions
  publication-title: Proc Int Conf Alg Learn Theory
– ident: ref288
  doi: 10.1109/TPAMI.2007.1030
– volume: 3
  start-page: 1137
  year: 2003
  ident: ref14
  article-title: A neural probabilistic language model
  publication-title: J Mach Learn Res
– ident: ref208
  doi: 10.1109/EuroSP.2016.36
– start-page: 1
  year: 2017
  ident: ref109
  article-title: A baseline for detecting misclassified and out-of-distribution examples in neural networks
  publication-title: Proc Int Conf Learn Represent
– ident: ref120
  doi: 10.1109/TPAMI.2014.2307881
– ident: ref33
  doi: 10.1109/TPAMI.2016.2587647
– ident: ref132
  doi: 10.1016/j.compmedimag.2014.11.010
– ident: ref284
  doi: 10.1023/A:1022699900025
– ident: ref56
  doi: 10.1016/S0004-3702(96)00034-3
– year: 2016
  ident: ref86
  publication-title: Deep Learning
– ident: ref341
  doi: 10.1109/ICCV.2015.11
– ident: ref24
  doi: 10.1613/jair.606
– ident: ref268
  doi: 10.1109/CVPR.2015.7298594
– ident: ref213
  doi: 10.1109/CVPR.2017.240
– ident: ref121
  doi: 10.1613/jair.1872
– ident: ref271
  doi: 10.1109/CVPR.2018.00582
– ident: ref113
  doi: 10.1109/ICRA.2016.7487708
– start-page: 3079
  year: 2015
  ident: ref51
  article-title: Semi-supervised sequence learning
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref240
  doi: 10.1016/j.patcog.2010.05.010
– ident: ref192
  doi: 10.1109/CVPR.2017.17
– ident: ref322
  doi: 10.1007/978-3-319-46487-9_40
– ident: ref283
  doi: 10.1109/CVPR.2017.316
– ident: ref21
  doi: 10.1145/279943.279962
– start-page: 517
  year: 2017
  ident: ref22
  article-title: Unsupervised learning by predicting noise
  publication-title: Proc Int Conf Mach Learn
– ident: ref29
  doi: 10.1109/CVPR.2018.00429
– ident: ref201
  doi: 10.1007/978-3-319-46466-4_5
– ident: ref219
  doi: 10.1109/CVPR.2018.00610
– year: 2018
  ident: ref165
  article-title: G-Distillation: Reducing overconfident errors on novel samples
  publication-title: arXiv 1804 03166v1
– year: 2018
  ident: ref228
  article-title: Do CIFAR-10 classifiers generalize to CIFAR-10?
  publication-title: arXiv 1806 00451
– start-page: 4967
  year: 2017
  ident: ref241
  article-title: A simple neural network module for relational reasoning
  publication-title: Proc Adv Neural Inf Process Syst
– year: 2016
  ident: ref148
  article-title: Adversarial examples in the physical world
  publication-title: arXiv 1607 02533
– ident: ref332
  doi: 10.1109/CVPR.2016.485
– year: 1995
  ident: ref18
  publication-title: Neural Networks for Pattern Recognition
– ident: ref68
  doi: 10.1109/TPAMI.2006.79
– ident: ref275
  doi: 10.1016/j.patrec.2008.03.010
– start-page: 1
  year: 2019
  ident: ref162
  article-title: Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting
  publication-title: Proc Int Conf Mach Learn
– ident: ref227
  doi: 10.1109/CVPR.2017.587
– ident: ref281
  doi: 10.1109/TPAMI.2011.52
– ident: ref131
  doi: 10.1007/s11263-013-0693-1
– ident: ref190
  doi: 10.1109/TPAMI.2018.2858821
– ident: ref168
  doi: 10.1109/ICPR.2010.813
– ident: ref232
  doi: 10.1109/TPAMI.2018.2849989
– ident: ref66
  doi: 10.1109/TPAMI.2010.109
– start-page: 1049
  year: 2009
  ident: ref183
  article-title: On the design of loss functions for classification: Theory, robustness to outliers, and savageboost
  publication-title: Proc Adv Neural Inf Process Syst
– year: 2013
  ident: ref140
  article-title: Auto-encoding variational Bayes
  publication-title: arXiv 1312 6114
– start-page: 2255
  year: 2017
  ident: ref279
  article-title: Few-shot learning through an information retrieval lens
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref153
  doi: 10.1561/0600000027
– ident: ref220
  doi: 10.1109/CVPR.2016.247
– volume: 15
  start-page: 1929
  year: 2014
  ident: ref258
  article-title: Dropout: A simple way to prevent neural networks from overfitting
  publication-title: J Mach Learn Res
– ident: ref282
  doi: 10.1109/ICCV.2015.463
– ident: ref235
  doi: 10.1109/TPAMI.2018.2814042
– ident: ref163
  doi: 10.1109/TPAMI.2017.2739147
– ident: ref184
  doi: 10.1109/TKDE.2010.61
– ident: ref177
  doi: 10.1109/TITS.2016.2598356
– ident: ref12
  doi: 10.1109/CVPR.2016.173
– start-page: 98
  year: 2018
  ident: ref105
  article-title: Exemplar-supported generative reproduction for class incremental learning
  publication-title: Proc Brit Mach Vis Conf
– ident: ref13
  doi: 10.1109/TPAMI.2013.50
– start-page: 235
  year: 2016
  ident: ref17
  article-title: Integrated perception with recurrent multi-task neural networks
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref107
  doi: 10.1109/CVPR.2016.90
– ident: ref43
  doi: 10.1109/TIT.1970.1054406
– ident: ref152
  doi: 10.1126/science.aab3050
– ident: ref199
  doi: 10.1109/TPAMI.2015.2461544
– volume: 31
  start-page: 2211
  year: 2009
  ident: ref265
  article-title: Ordinal measures for iris recognition
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2008.240
– start-page: 489
  year: 1996
  ident: ref277
  article-title: Discovering structure in multiple learning tasks: The TC algorithm
  publication-title: Proc Int Conf Mach Learn
– ident: ref134
  doi: 10.1016/j.ins.2017.11.061
– ident: ref193
  doi: 10.1109/CVPR.2016.282
– start-page: 1
  year: 2018
  ident: ref239
  article-title: Defense-GAN: Protecting classifiers against adversarial attacks using generative models
  publication-title: Proc Int Conf Learn Represent
– ident: ref136
  doi: 10.1007/978-94-015-8630-6
– ident: ref305
  doi: 10.1109/TPAMI.2018.2857768
– ident: ref253
  doi: 10.1016/S0378-3758(00)00115-4
– ident: ref170
  doi: 10.1007/s100320200076
– ident: ref218
  doi: 10.1023/A:1007601015854
– start-page: 37
  year: 2014
  ident: ref166
  article-title: Robust classification under sample selection bias
  publication-title: Proc Adv Neural Inf Process Syst
– start-page: 1540
  year: 2015
  ident: ref215
  article-title: Lifelong learning with non-iid tasks
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref102
  doi: 10.1109/TPAMI.1983.4767411
– ident: ref147
  doi: 10.1002/0471660264
– year: 2018
  ident: ref54
  article-title: BERT: Pre-training of deep bidirectional transformers for language understanding
  publication-title: arXiv 1810 04805
– ident: ref67
  doi: 10.1109/MSP.2017.2740965
– year: 2017
  ident: ref321
  article-title: Recent advances in transfer learning for cross-dataset visual recognition: A problem-oriented perspective
  publication-title: arXiv 1705 04396
– ident: ref200
  doi: 10.1109/CVPR.2015.7298640
– ident: ref172
  doi: 10.1109/TPAMI.2015.2456899
– start-page: 1621
  year: 2011
  ident: ref326
  article-title: Pattern field classification with style normalized transformation
  publication-title: Proc Int Joint Conf Artif Intell
– ident: ref244
  doi: 10.1109/TNN.2008.2005605
– ident: ref111
  doi: 10.1109/34.273716
– ident: ref158
  doi: 10.1109/5.726791
– ident: ref42
  doi: 10.1109/TMM.2015.2477044
– start-page: 1
  year: 2016
  ident: ref331
  article-title: Stacked what-where auto-encoders
  publication-title: Proc Workshop Int Conf Learn Represent
– start-page: 1986
  year: 2017
  ident: ref45
  article-title: Consistent multitask learning with nonlinear output relations
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref145
  doi: 10.1109/CVPR.2018.00363
– ident: ref144
  doi: 10.1142/p191
– ident: ref125
  doi: 10.1109/34.824819
– ident: ref214
  doi: 10.1109/TPAMI.2017.2723882
– ident: ref246
  doi: 10.1109/TPAMI.2012.256
– start-page: 6670
  year: 2017
  ident: ref194
  article-title: Few-shot adversarial domain adaptation
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref242
  doi: 10.1147/JRD.2017.2701178
– ident: ref117
  doi: 10.1109/TPAMI.2011.283
– ident: ref82
  doi: 10.1016/j.neucom.2014.09.081
– start-page: 1
  year: 2015
  ident: ref230
  article-title: Training deep neural networks on noisy labels with bootstrapping
  publication-title: Proc Workshop Int Conf Learn Represent
– ident: ref301
  doi: 10.1109/CVPR.2018.00760
– start-page: 4296
  year: 2016
  ident: ref196
  article-title: Adaptive smoothed online multi-task learning
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref311
  doi: 10.1109/CVPR.2018.00417
– ident: ref50
  doi: 10.1109/TASL.2011.2134090
– ident: ref298
  doi: 10.1109/TPAMI.2011.264
– ident: ref47
  doi: 10.1145/1390156.1390177
– year: 2001
  ident: ref63
  publication-title: Pattern Classification
– ident: ref313
  doi: 10.1109/CVPR.2018.00366
– ident: ref38
  doi: 10.1145/3133944.3133949
– ident: ref293
  doi: 10.1109/CVPR.2018.00950
– ident: ref32
  doi: 10.1023/A:1007379606734
– ident: ref72
  doi: 10.1109/TNNLS.2013.2292894
– start-page: 3320
  year: 2014
  ident: ref315
  article-title: How transferable are features in deep neural networks?
  publication-title: Proc Adv Neural Inf Process Syst
– ident: ref124
  doi: 10.1016/j.patrec.2009.09.011
– start-page: 612
  year: 2016
  ident: ref328
  article-title: Augmenting supervised neural networks with unsupervised objectives for large-scale image classification
  publication-title: Proc Int Conf Mach Learn
– start-page: 1
  year: 2017
  ident: ref226
  article-title: Optimization as a model for few-shot learning
  publication-title: Proc Int Conf Learn Represent
– year: 2017
  ident: ref260
  article-title: One pixel attack for fooling deep neural networks
  publication-title: arXiv 1710 08864
– ident: ref300
  doi: 10.1109/CVPR.2018.00906
– start-page: 1
  year: 2018
  ident: ref96
  article-title: Deep nearest class mean classifiers
  publication-title: Proc Worskhop Int Conf Learn Represent
– year: 2001
  ident: ref273
  article-title: One-class classification: Concept-learning in the absence of counter-examples
– start-page: 1
  year: 2017
  ident: ref317
  article-title: Understanding deep learning requires rethinking generalization
  publication-title: Proc Int Conf Learn Represent
– ident: ref270
  doi: 10.1109/CVPR.2014.220
– ident: ref204
  doi: 10.1109/CVPR.2019.01158
– ident: ref114
  doi: 10.1007/978-3-642-33709-3_50
– ident: ref202
  doi: 10.1561/0600000033
– start-page: 536
  year: 2006
  ident: ref310
  article-title: Robust support vector machine training via convex outlier ablation
  publication-title: Proc AAAI Conf Artif Intell
– ident: ref264
  doi: 10.1109/TPAMI.2015.2505293
– ident: ref304
  doi: 10.1109/CVPR.2018.00393
– ident: ref308
  doi: 10.1109/TNNLS.2016.2637351
– ident: ref91
  doi: 10.1145/1143844.1143891
– ident: ref57
  doi: 10.1109/ICCV.2015.167
– start-page: 1
  year: 2018
  ident: ref83
  article-title: Unsupervised representation learning by predicting image rotations
  publication-title: Proc Int Conf Learn Represent
– ident: ref188
  doi: 10.1109/CVPR.2016.433
– ident: ref6
  doi: 10.1109/CVPR.2005.283
SSID ssj0003563
Score 2.6369932
SecondaryResourceType review_article
Snippet The accuracies for many pattern recognition tasks have increased rapidly year by year, achieving or even outperforming human performance. From the perspective...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 894
SubjectTerms Accuracy
Big Data
Changing environments
Clean and big data
closed world
Distributed control
Human performance
Identification methods
independent and identically distributed
Machine intelligence
Machine learning
Neural networks
Pattern recognition
Pattern recognition systems
robust pattern recognition
Robustness
Task analysis
Task complexity
Title Towards Robust Pattern Recognition: A Review
URI https://ieeexplore.ieee.org/document/9103349
https://www.proquest.com/docview/2408657711
Volume 108
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8MwDLa2neDAayAGA_XAjXVrmqZpuE2IaZo0mKZN2q1K0uQC6hDrLvx6krSdeAlxyyGJIjuO7dj-DHAjYxEliFOfcW4dlIT7QsTEx0ToiCWJiFy4YPoYj5fRZEVWDejtamGUUi75TPXt0MXys7Xc2q-ygVFtGEesCU3juJW1WrtXF5OqaxoyAmzEsC6QCdhgMps_3RtXMAz6Fm-cJuEXJeS6qvx4ip1-GR3CtD5ZmVby3N8Woi_fv4E2_vfoR3BQGZresLwZx9BQ-Qnsf4IfbENv4XJmN958Lbabwps5rM3cm9dJRev8zht6ZfjgFJajh8X92K-6J_gyZKTwsywzVMLcKJ9MIKSM4cM1QpiGylgZMQmJkDyRGIlII40DiRRVTGkd0gzrKMZn0MrXuToHL0EBl1RpzJCKMhIIpJjOuCYhpzjhsgOoJmcqK2hx2-HiJXUuRsBSx4LUsiCtWNCB292a1xJY48_ZbUvT3cyKnB3o1lxLK9nbpBa0LSaUInTx-6pL2LN7lwlfXWgVb1t1ZUyLQly7O_UBMfjIkA
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8MwDLbGOAAH3ojBgB64QUfTNE3DDSGmMdiYpiFxq5I0uYA6xLoLv54kbSdeQtxySJTIjmM7tj8DnMpYRAni1GecWwcl4b4QMfExETpiSSIiFy4YDOPeY9R_Ik8NOF_UwiilXPKZ6tihi-VnUzm3X2UXRrVhHLElWDZ6n6CyWmvx7mJS9U1DRoSNINYlMgG76I_GD9fGGQyDjkUcp0n4RQ25vio_HmOnYbobMKjPViaWPHfmhejI92-wjf89_CasV6amd1XejS1oqHwb1j4BEO7A-cRlzc688VTMZ4U3cmibuTeu04qm-aV35ZUBhF147N5Mrnt-1T_BlyEjhZ9lmXFwMTfqJxMIKWP6cI0QpqEydkZMQiIkTyRGItJI40AiRRVTWoc0wzqK8R4082mu9sFLUMAlVRozpKKMBAIppjOuScgpTrhsAarJmcoKXNz2uHhJnZMRsNSxILUsSCsWtOBssea1hNb4c_aOpeliZkXOFrRrrqWV9M1SC9sWE0oROvh91Qms9CaD-_T-dnh3CKt2nzL9qw3N4m2ujoyhUYhjd78-ANeiy9k
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=Towards+Robust+Pattern+Recognition%3A+A+Review&rft.jtitle=Proceedings+of+the+IEEE&rft.au=Zhang%2C+Xu-Yao&rft.au=Liu%2C+Cheng-Lin&rft.au=Suen%2C+Ching+Y.&rft.date=2020-06-01&rft.issn=0018-9219&rft.eissn=1558-2256&rft.volume=108&rft.issue=6&rft.spage=894&rft.epage=922&rft_id=info:doi/10.1109%2FJPROC.2020.2989782&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JPROC_2020_2989782
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9219&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9219&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9219&client=summon