A Survey on Label-Efficient Deep Image Segmentation: Bridging the Gap Between Weak Supervision and Dense Prediction

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on pattern analysis and machine intelligence Ročník 45; číslo 8; s. 9284 - 9305
Hlavní autoři: Shen, Wei, Peng, Zelin, Wang, Xuehui, Wang, Huayu, Cen, Jiazhong, Jiang, Dongsheng, Xie, Lingxi, Yang, Xiaokang, Tian, Qi
Médium: Journal Article
Jazyk:angličtina
Vydáno: 01.08.2023
ISSN:0162-8828, 2160-9292
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Author Yang, Xiaokang
Peng, Zelin
Tian, Qi
Shen, Wei
Xie, Lingxi
Jiang, Dongsheng
Wang, Huayu
Cen, Jiazhong
Wang, Xuehui
Author_xml – sequence: 1
  givenname: Wei
  orcidid: 0000-0002-1235-598X
  surname: Shen
  fullname: Shen, Wei
  organization: MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China
– sequence: 2
  givenname: Zelin
  surname: Peng
  fullname: Peng, Zelin
  organization: MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China
– sequence: 3
  givenname: Xuehui
  orcidid: 0000-0002-6333-7773
  surname: Wang
  fullname: Wang, Xuehui
  organization: MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China
– sequence: 4
  givenname: Huayu
  surname: Wang
  fullname: Wang, Huayu
  organization: MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China
– sequence: 5
  givenname: Jiazhong
  orcidid: 0000-0002-2165-6418
  surname: Cen
  fullname: Cen, Jiazhong
  organization: MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China
– sequence: 6
  givenname: Dongsheng
  surname: Jiang
  fullname: Jiang, Dongsheng
  organization: Huawei Inc., Shenzhen, Guangdong, China
– sequence: 7
  givenname: Lingxi
  orcidid: 0000-0003-4831-9451
  surname: Xie
  fullname: Xie, Lingxi
  organization: Huawei Inc., Shenzhen, Guangdong, China
– sequence: 8
  givenname: Xiaokang
  orcidid: 0000-0003-4029-3322
  surname: Yang
  fullname: Yang, Xiaokang
  organization: MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China
– sequence: 9
  givenname: Qi
  orcidid: 0000-0002-7252-5047
  surname: Tian
  fullname: Tian, Qi
  organization: Huawei Inc., Shenzhen, Guangdong, China
BookMark eNp9kE1PwkAQhjcGEwH9A572DxRntx9svQEiNsFIAsZjsy2zdRW2zW7F8O_dCicPniaZzPPmnWdAeqY2SMgtgxFjkN5tVpPnbMSBh6OQRwkDfkH6nCUQpDzlPdIHlvBACC6uyMC5DwAWxRD2iZvQ9Zc94JHWhi5lgbtgrpQuNZqWPiA2NNvLCukaq71fyVbX5p5Ord5W2lS0fUe6kA2dYvuNaOgbyk8f2KA9aOdPqTRbH2Mc0pXFrS47_ppcKrlzeHOeQ_L6ON_MnoLlyyKbTZZB6cu2AYpQKJTMt5YSWBhHkEQSSjlGIceAjHMRFwJC_ycKBVwUKk1SxcYQFx0wJPyUW9raOYsqb6zeS3vMGeSdtvxXW95py8_aPCT-QKU-vd1aqXf_oT-QbHP2
CitedBy_id crossref_primary_10_1109_JBHI_2024_3385098
crossref_primary_10_1007_s00371_024_03623_9
crossref_primary_10_1016_j_inffus_2024_102311
crossref_primary_10_1007_s00371_024_03373_8
crossref_primary_10_3390_math12162520
crossref_primary_10_1016_j_aei_2025_103254
crossref_primary_10_1109_TIFS_2025_3571665
crossref_primary_10_1016_j_rse_2024_114274
crossref_primary_10_1016_j_media_2024_103183
crossref_primary_10_1016_j_media_2025_103745
crossref_primary_10_3390_rs17050808
crossref_primary_10_1016_j_compscitech_2024_110713
crossref_primary_10_1016_j_patcog_2024_110492
crossref_primary_10_1109_TMI_2024_3508738
crossref_primary_10_1016_j_compmedimag_2024_102438
crossref_primary_10_1016_j_eswa_2025_127497
crossref_primary_10_1016_j_neucom_2025_130293
crossref_primary_10_1109_TGRS_2023_3330479
crossref_primary_10_1007_s00371_025_03843_7
crossref_primary_10_1016_j_eswa_2024_123564
crossref_primary_10_1038_s41598_025_12969_6
crossref_primary_10_1016_j_neunet_2024_106581
crossref_primary_10_1016_j_rse_2023_113779
crossref_primary_10_1109_ACCESS_2024_3484430
crossref_primary_10_3390_rs16050804
crossref_primary_10_3390_s25010225
crossref_primary_10_1016_j_inffus_2025_103590
crossref_primary_10_1016_j_imavis_2024_105149
crossref_primary_10_1016_j_imavis_2025_105527
crossref_primary_10_1016_j_neucom_2025_129589
crossref_primary_10_1109_TGRS_2024_3373908
crossref_primary_10_1109_TGRS_2025_3559901
crossref_primary_10_1016_j_compag_2023_108412
crossref_primary_10_1016_j_engappai_2025_111325
crossref_primary_10_1016_j_neunet_2025_107215
crossref_primary_10_1109_TIP_2025_3573509
crossref_primary_10_1016_j_media_2024_103329
crossref_primary_10_1109_TCSVT_2024_3515088
crossref_primary_10_1007_s11517_024_03195_9
crossref_primary_10_3390_s24030997
crossref_primary_10_1109_LRA_2024_3505779
crossref_primary_10_3390_rs16030526
crossref_primary_10_1109_TGRS_2023_3323926
crossref_primary_10_1109_ACCESS_2025_3572013
crossref_primary_10_1145_3707447
crossref_primary_10_1016_j_measurement_2025_118610
crossref_primary_10_1109_TCYB_2024_3403729
crossref_primary_10_3390_atmos14121813
crossref_primary_10_1109_TPAMI_2025_3557047
crossref_primary_10_1080_17538947_2025_2491108
crossref_primary_10_1007_s11263_025_02421_7
crossref_primary_10_1002_tee_70014
crossref_primary_10_3390_ijms26157134
crossref_primary_10_1016_j_engappai_2025_111100
crossref_primary_10_1109_TPAMI_2025_3566593
crossref_primary_10_1109_TPAMI_2024_3416302
crossref_primary_10_1109_LSP_2023_3343945
crossref_primary_10_1016_j_ultrasmedbio_2025_05_026
Cites_doi 10.1007/s11263-022-01653-1
10.1080/24709360.2019.1670513
10.5555/3295222.3295309
10.1109/ICCV.2015.164
10.1109/CVPR46437.2021.00265
10.1007/978-3-319-10602-1_48
10.1109/TPAMI.2018.2858821
10.1109/CVPR.2018.00780
10.1109/CVPR.2019.00262
10.1109/ICCV.2017.322
10.1007/978-3-030-58536-5_21
10.1109/CVPR.2018.00445
10.1109/ICCV48922.2021.00690
10.1007/978-3-031-20056-4_29
10.1109/CVPR.2015.7298965
10.1109/WACV48630.2021.00106
10.1145/3400066
10.1109/CVPR.2019.00231
10.1007/978-3-030-58571-6_9
10.1109/CVPR.2019.00323
10.5555/2969033.2969125
10.1109/ICCV48922.2021.00689
10.1109/CVPR.2018.00473
10.1109/ICCV48922.2021.00692
10.1109/CVPR52688.2022.01553
10.1109/CVPR.2018.00399
10.1109/CVPR.2019.00541
10.1145/3474085.3475675
10.1109/CVPR.2017.472
10.1109/WACV48630.2021.00142
10.48550/arXiv.1802.02611
10.1109/CVPR46437.2021.01641
10.1109/CVPR.2016.352
10.1007/978-3-031-20077-9_21
10.1109/ICCV48922.2021.00990
10.1007/s10462-019-09792-7
10.1007/978-3-319-24574-4_28
10.1109/ICCV.2015.191
10.1109/CVPR46437.2021.00304
10.1007/978-3-319-10584-0_20
10.48550/ARXIV.1412.7062
10.1109/TNN.2008.2005605
10.1109/CVPR.2016.319
10.1109/ICCV48922.2021.00868
10.1007/978-3-319-46493-0_42
10.1109/ICCV48922.2021.00895
10.1109/ICCV48922.2021.00060
10.1109/CVPR.2018.00913
10.1109/CVPR.2018.00733
10.1023/A:1011174803800
10.1109/ICCV48922.2021.00685
10.1109/CVPR.2017.687
10.1109/CVPR42600.2020.00431
10.1109/TPAMI.2004.60
10.1109/CVPR52688.2022.00426
10.1109/CVPR46437.2021.01223
10.1109/CVPR52688.2022.01129
10.1109/CVPR52688.2022.00969
10.1109/ICCV48922.2021.00675
10.1109/TPAMI.2015.2389824
10.1609/aaai.v35i2.16269
10.1109/CVPR42600.2020.00901
10.1109/ICCV.2019.00344
10.1007/978-3-319-46475-6_7
10.1109/CVPR.2017.660
10.1109/CVPR52688.2022.00444
10.1109/ITW.2015.7133169
10.1109/TPAMI.2006.233
10.1109/CVPR.2017.315
10.1109/ICCV.2019.00743
10.1109/34.295913
10.1109/TPAMI.2016.2644615
10.1109/ICCV48922.2021.00951
10.1609/aaai.v35i3.16294
10.1109/ICCV48922.2021.01507
10.1109/CVPR.2019.00325
10.1007/978-3-030-58601-0_26
10.1109/CVPR.2017.181
10.1145/1015706.1015720
10.1007/978-3-030-58523-5_38
10.1609/aaai.v34i07.6971
10.1109/CVPR.2017.563
10.1109/CVPR46437.2021.01642
10.1007/978-3-030-01267-0_7
10.1007/978-3-030-58598-3_23
10.1109/ICCV.2019.00612
10.1109/CVPR52688.2022.01634
10.1109/CVPR46437.2021.00540
10.1109/ICCV.2019.00996
10.1109/ICCV48922.2021.00719
10.1109/ICCV48922.2021.00715
10.1109/CVPR.2018.00132
10.1109/CVPR42600.2020.01032
10.1109/ICCV48922.2021.00282
10.1609/aaai.v36i2.20034
10.1007/978-3-030-01219-9_18
10.5555/3495724.3497510
10.1109/ICCV48922.2021.00693
10.1109/CVPR42600.2020.00975
10.1109/ICCV.2017.74
10.1109/CVPR52688.2022.00427
10.1109/ICCV.2019.00930
10.1109/WACV.2018.00097
10.1109/CVPR46437.2021.00267
10.1109/CVPR46437.2021.00264
10.1109/TIP.2022.3144036
10.1109/ICCV48922.2021.00718
10.1109/CVPR52688.2022.01131
10.1109/TPAMI.2017.2699184
10.1109/ICCV48922.2021.00809
10.1109/CVPR52688.2022.01638
10.1109/CVPR.2018.00523
10.1145/3394171.3413593
10.1007/s11263-013-0620-5
10.1109/CVPR46437.2021.00684
10.1007/978-3-030-58583-9_18
10.1109/CVPR46437.2021.00681
10.1109/CVPR.2018.00759
10.1109/CVPR.2018.00144
10.1109/CVPR.2019.00326
10.1109/CVPR42600.2020.01299
10.1007/s11263-020-01293-3
10.48550/ARXIV.1706.03762
10.1109/ICCV48922.2021.00717
10.1109/CVPR46437.2021.00406
10.1109/ICCV.2019.00925
10.1007/978-1-4899-7502-7_79-1
10.1007/978-3-030-01270-0_31
10.1109/CVPR42600.2020.01229
10.1109/CVPR46437.2021.01549
10.1109/34.868688
10.1007/s11263-021-01465-9
10.1007/s11263-014-0733-5
10.5555/3524938.3525087
10.1109/CVPR.2016.344
10.1109/CVPR52688.2022.01378
10.1109/CVPR.2019.00976
10.1109/CVPR.2014.49
10.1109/CVPR52688.2022.01760
10.1109/CVPR.2019.00963
10.1109/CVPR.2019.00710
10.1109/CVPR.2018.00195
10.1109/ICCV.2003.1238308
10.1109/CVPR42600.2020.00434
10.1609/aaai.v34i07.6705
10.1109/TPAMI.2016.2537320
10.1109/CVPR.2016.350
10.48550/arXiv.2010.11929
10.1109/CVPR.2017.326
10.1109/CVPR46437.2021.01009
10.1109/CVPR.2018.00147
10.1109/CVPR52688.2022.00263
10.1109/CVPR46437.2021.01652
10.1109/CVPR46437.2021.00126
10.1109/ICCV.2019.00216
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.1109/TPAMI.2023.3246102
DatabaseName CrossRef
DatabaseTitle CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 2160-9292
EndPage 9305
ExternalDocumentID 10_1109_TPAMI_2023_3246102
GroupedDBID ---
-DZ
-~X
.DC
0R~
29I
4.4
53G
5GY
5VS
6IK
97E
9M8
AAJGR
AASAJ
AAWTH
AAYXX
ABFSI
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
ADRHT
AENEX
AETEA
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CITATION
CS3
DU5
E.L
EBS
EJD
F5P
FA8
HZ~
H~9
IBMZZ
ICLAB
IEDLZ
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNI
RNS
RXW
RZB
TAE
TN5
UHB
VH1
~02
ID FETCH-LOGICAL-c162t-e838fea1882aa01354064a0ca7e8a70e12285b803216e8f028bf969f1705ba013
ISSN 0162-8828
IngestDate Tue Nov 18 21:24:08 EST 2025
Sat Nov 29 02:58:23 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 8
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 OpenURL
MergedId FETCHMERGED-LOGICAL-c162t-e838fea1882aa01354064a0ca7e8a70e12285b803216e8f028bf969f1705ba013
ORCID 0000-0002-6333-7773
0000-0003-4831-9451
0000-0002-2165-6418
0000-0002-7252-5047
0000-0003-4029-3322
0000-0002-1235-598X
PageCount 22
ParticipantIDs crossref_primary_10_1109_TPAMI_2023_3246102
crossref_citationtrail_10_1109_TPAMI_2023_3246102
PublicationCentury 2000
PublicationDate 2023-8-00
PublicationDateYYYYMMDD 2023-08-01
PublicationDate_xml – month: 08
  year: 2023
  text: 2023-8-00
PublicationDecade 2020
PublicationTitle IEEE transactions on pattern analysis and machine intelligence
PublicationYear 2023
References ref57
ref56
ref59
ref58
ref53
ref52
ref55
ref168
ref54
ref169
Bao (ref177)
ref178
ref51
Xie (ref174)
ref176
ref173
ref172
ref45
ref48
ref47
ref42
ref41
ref44
ref43
Zou (ref30)
ref49
ref8
ref180
ref181
ref4
ref3
ref6
ref5
Lee (ref90)
ref100
ref101
ref40
ref186
ref184
Hsu (ref39)
ref182
ref183
ref35
ref34
ref37
ref36
ref31
ref148
ref33
ref146
ref32
ref147
ref38
ref155
ref156
ref153
ref154
ref151
ref152
ref150
ref23
Laradji (ref115)
ref26
ref25
Radford (ref158)
ref20
French (ref137)
ref159
ref22
ref157
ref21
Yu (ref171)
ref28
ref27
ref29
ref166
Chen (ref9) 2017
ref167
ref164
ref165
Hou (ref46)
ref163
ref161
Li (ref162)
ref13
ref12
ref15
ref128
ref14
ref129
ref97
ref126
ref96
ref127
ref11
ref99
ref124
ref10
ref98
ref125
ref17
ref16
ref19
ref18
Hamilton (ref24)
ref93
ref133
ref134
ref131
ref132
ref130
ref91
ref89
ref139
ref86
ref85
ref138
ref88
ref135
ref87
ref136
Zhang (ref78)
Pan (ref149)
Han (ref170)
Pinheiro (ref74)
Srivastava (ref94) 2014; 15
ref82
ref144
ref81
ref145
Yuan (ref175)
ref84
ref142
ref83
ref143
ref140
ref141
ref80
ref79
ref108
Caron (ref72)
ref109
Bucher (ref160)
Tarvainen (ref185)
ref106
ref107
ref75
ref104
ref105
ref77
ref102
ref76
ref103
ref1
Zhou (ref179)
Hung (ref50)
Yu (ref7)
Krähenbühl (ref2)
ref71
ref111
ref70
ref112
ref73
ref110
ref68
ref119
ref67
ref117
ref69
ref118
ref64
ref63
ref116
ref66
ref113
ref65
ref114
Saxe (ref95)
Zhang (ref92)
ref60
ref122
ref123
ref62
ref120
ref61
ref121
References_xml – ident: ref159
  doi: 10.1007/s11263-022-01653-1
– ident: ref97
  doi: 10.1080/24709360.2019.1670513
– ident: ref156
  doi: 10.5555/3295222.3295309
– ident: ref133
  doi: 10.1109/ICCV.2015.164
– ident: ref182
  doi: 10.1109/CVPR46437.2021.00265
– start-page: 466
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref160
  article-title: Zero-shot semantic segmentation
– ident: ref62
  doi: 10.1007/978-3-319-10602-1_48
– ident: ref186
  doi: 10.1109/TPAMI.2018.2858821
– ident: ref143
  doi: 10.1109/CVPR.2018.00780
– start-page: 1
  volume-title: Proc. Brit. Mach. Vis. Conf.
  ident: ref50
  article-title: Adversarial learning for semi-supervised semantic segmentation
– ident: ref152
  doi: 10.1109/CVPR.2019.00262
– ident: ref12
  doi: 10.1109/ICCV.2017.322
– ident: ref104
  doi: 10.1007/978-3-030-58536-5_21
– ident: ref32
  doi: 10.1109/CVPR.2018.00445
– ident: ref101
  doi: 10.1109/ICCV48922.2021.00690
– ident: ref77
  doi: 10.1007/978-3-031-20056-4_29
– ident: ref20
  doi: 10.1109/CVPR.2015.7298965
– ident: ref117
  doi: 10.1109/WACV48630.2021.00106
– ident: ref22
  doi: 10.1145/3400066
– ident: ref49
  doi: 10.1109/CVPR.2019.00231
– ident: ref64
  doi: 10.1007/978-3-030-58571-6_9
– ident: ref116
  doi: 10.1109/CVPR.2019.00323
– ident: ref151
  doi: 10.5555/2969033.2969125
– ident: ref163
  doi: 10.1109/ICCV48922.2021.00689
– ident: ref144
  doi: 10.1109/CVPR.2018.00473
– ident: ref93
  doi: 10.1109/ICCV48922.2021.00692
– ident: ref178
  doi: 10.1109/CVPR52688.2022.01553
– ident: ref34
  doi: 10.1109/CVPR.2018.00399
– ident: ref85
  doi: 10.1109/CVPR.2019.00541
– ident: ref110
  doi: 10.1145/3474085.3475675
– ident: ref11
  doi: 10.1109/CVPR.2017.472
– ident: ref51
  doi: 10.1109/WACV48630.2021.00142
– ident: ref10
  doi: 10.48550/arXiv.1802.02611
– ident: ref76
  doi: 10.1109/CVPR46437.2021.01641
– ident: ref61
  doi: 10.1109/CVPR.2016.352
– ident: ref122
  doi: 10.1007/978-3-031-20077-9_21
– start-page: 1195
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref185
  article-title: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
– ident: ref23
  doi: 10.1109/ICCV48922.2021.00990
– ident: ref21
  doi: 10.1007/s10462-019-09792-7
– ident: ref5
  doi: 10.1007/978-3-319-24574-4_28
– ident: ref54
  doi: 10.1109/ICCV.2015.191
– ident: ref75
  doi: 10.1109/CVPR46437.2021.00304
– ident: ref3
  doi: 10.1007/978-3-319-10584-0_20
– ident: ref6
  doi: 10.48550/ARXIV.1412.7062
– ident: ref105
  doi: 10.1109/TNN.2008.2005605
– ident: ref81
  doi: 10.1109/CVPR.2016.319
– ident: ref150
  doi: 10.1109/ICCV48922.2021.00868
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref24
  article-title: Unsupervised semantic segmentation by distilling feature correspondences
– ident: ref107
  doi: 10.1007/978-3-319-46493-0_42
– ident: ref145
  doi: 10.1109/ICCV48922.2021.00895
– ident: ref169
  doi: 10.1109/ICCV48922.2021.00060
– ident: ref14
  doi: 10.1109/CVPR.2018.00913
– ident: ref108
  doi: 10.1109/CVPR.2018.00733
– ident: ref71
  doi: 10.1023/A:1011174803800
– ident: ref135
  doi: 10.1109/ICCV48922.2021.00685
– ident: ref86
  doi: 10.1109/CVPR.2017.687
– volume: 15
  start-page: 1929
  issue: 1
  year: 2014
  ident: ref94
  article-title: Dropout: A simple way to prevent neural networks from overfitting
  publication-title: J. Mach. Learn. Res.
– ident: ref183
  doi: 10.1109/CVPR42600.2020.00431
– ident: ref130
  doi: 10.1109/TPAMI.2004.60
– ident: ref106
  doi: 10.1109/CVPR52688.2022.00426
– ident: ref42
  doi: 10.1109/CVPR46437.2021.01223
– ident: ref165
  doi: 10.1109/CVPR52688.2022.01129
– ident: ref146
  doi: 10.1109/CVPR52688.2022.00969
– ident: ref168
  doi: 10.1109/ICCV48922.2021.00675
– ident: ref119
  doi: 10.1109/TPAMI.2015.2389824
– ident: ref100
  doi: 10.1609/aaai.v35i2.16269
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref30
  article-title: PseudoSeg: Designing pseudo labels for semantic segmentation
– ident: ref91
  doi: 10.1109/CVPR42600.2020.00901
– ident: ref35
  doi: 10.1109/ICCV.2019.00344
– ident: ref60
  doi: 10.1007/978-3-319-46475-6_7
– start-page: 1
  volume-title: Proc. Brit. Mach. Vis. Conf.
  ident: ref115
  article-title: Where are the masks: Instance segmentation with image-level supervision
– start-page: 7281
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref175
  article-title: HRFormer: High-resolution vision transformer for dense predict
– ident: ref13
  doi: 10.1109/CVPR.2017.660
– ident: ref181
  doi: 10.1109/CVPR52688.2022.00444
– ident: ref96
  doi: 10.1109/ITW.2015.7133169
– ident: ref113
  doi: 10.1109/TPAMI.2006.233
– start-page: 532
  volume-title: Proc. Eur. Conf. Comput. Vis.
  ident: ref149
  article-title: Two-phase pseudo label densification for self-training based domain adaptation
– ident: ref132
  doi: 10.1109/CVPR.2017.315
– start-page: 12992
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref171
  article-title: Glance-and-gaze vision transformer
– ident: ref43
  doi: 10.1109/ICCV.2019.00743
– ident: ref111
  doi: 10.1109/34.295913
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref162
  article-title: Language-driven semantic segmentation
– ident: ref139
  doi: 10.1109/ICCV.2017.322
– ident: ref15
  doi: 10.1109/TPAMI.2016.2644615
– ident: ref176
  doi: 10.1109/ICCV48922.2021.00951
– ident: ref47
  doi: 10.1609/aaai.v35i3.16294
– ident: ref131
  doi: 10.1109/ICCV48922.2021.01507
– start-page: 655
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref92
  article-title: Causal intervention for weakly-supervised semantic segmentation
– ident: ref125
  doi: 10.1109/CVPR.2019.00325
– ident: ref136
  doi: 10.1007/978-3-030-58601-0_26
– start-page: 3285
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref78
  article-title: Looking beyond single images for contrastive semantic segmentation learning
– ident: ref38
  doi: 10.1109/CVPR.2017.181
– ident: ref1
  doi: 10.1145/1015706.1015720
– ident: ref18
  doi: 10.1007/978-3-030-58523-5_38
– ident: ref56
  doi: 10.1609/aaai.v34i07.6971
– ident: ref99
  doi: 10.1109/CVPR.2017.563
– ident: ref29
  doi: 10.1109/CVPR46437.2021.01642
– ident: ref40
  doi: 10.1007/978-3-030-01267-0_7
– start-page: 395
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref74
  article-title: Unsupervised learning of dense visual representations
– ident: ref141
  doi: 10.1007/978-3-030-58598-3_23
– ident: ref154
  doi: 10.1109/ICCV.2019.00612
– ident: ref114
  doi: 10.1109/CVPR52688.2022.01634
– ident: ref80
  doi: 10.1109/CVPR46437.2021.00540
– ident: ref44
  doi: 10.1109/ICCV.2019.00996
– start-page: 9912
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref72
  article-title: Unsupervised learning of visual features by contrasting cluster assignments
– ident: ref88
  doi: 10.1109/ICCV48922.2021.00719
– ident: ref102
  doi: 10.1109/ICCV48922.2021.00715
– ident: ref63
  doi: 10.1109/CVPR.2018.00132
– year: 2017
  ident: ref9
  article-title: Rethinking atrous convolution for semantic image segmentation
– ident: ref33
  doi: 10.1109/CVPR42600.2020.01032
– ident: ref140
  doi: 10.1109/ICCV48922.2021.00282
– ident: ref155
  doi: 10.1609/aaai.v36i2.20034
– ident: ref147
  doi: 10.1007/978-3-030-01219-9_18
– ident: ref69
  doi: 10.5555/3495724.3497510
– ident: ref142
  doi: 10.1109/ICCV48922.2021.00693
– ident: ref67
  doi: 10.1109/CVPR42600.2020.00975
– ident: ref82
  doi: 10.1109/ICCV.2017.74
– start-page: 12077
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref174
  article-title: SegFormer: Simple and efficient design for semantic segmentation with transformers
– ident: ref180
  doi: 10.1109/CVPR52688.2022.00427
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref179
  article-title: iBOT: Image bert pre-training with online tokenizer
– ident: ref53
  doi: 10.1109/ICCV.2019.00930
– ident: ref70
  doi: 10.1109/ICCV.2015.164
– ident: ref83
  doi: 10.1109/WACV.2018.00097
– ident: ref127
  doi: 10.1109/CVPR46437.2021.00267
– start-page: 27408
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref90
  article-title: Reducing information bottleneck for weakly supervised semantic segmentation
– ident: ref57
  doi: 10.1109/CVPR46437.2021.00264
– ident: ref134
  doi: 10.1109/TIP.2022.3144036
– ident: ref138
  doi: 10.1109/ICCV48922.2021.00718
– ident: ref52
  doi: 10.1109/CVPR52688.2022.01131
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref177
  article-title: BEiT: Bert pre-training of image transformers
– ident: ref8
  doi: 10.1109/TPAMI.2017.2699184
– ident: ref120
  doi: 10.1109/ICCV48922.2021.00809
– ident: ref103
  doi: 10.1109/CVPR52688.2022.01638
– ident: ref26
  doi: 10.1109/CVPR.2018.00523
– ident: ref161
  doi: 10.1145/3394171.3413593
– ident: ref121
  doi: 10.1007/s11263-013-0620-5
– ident: ref37
  doi: 10.1109/CVPR46437.2021.00684
– ident: ref126
  doi: 10.1007/978-3-030-58583-9_18
– ident: ref172
  doi: 10.1109/CVPR46437.2021.00681
– ident: ref45
  doi: 10.1109/CVPR.2018.00759
– ident: ref87
  doi: 10.1109/CVPR.2018.00144
– ident: ref17
  doi: 10.1109/CVPR.2019.00326
– ident: ref148
  doi: 10.1109/CVPR42600.2020.01299
– ident: ref98
  doi: 10.1007/s11263-020-01293-3
– ident: ref166
  doi: 10.48550/ARXIV.1706.03762
– ident: ref173
  doi: 10.1109/ICCV48922.2021.00717
– ident: ref89
  doi: 10.1109/CVPR46437.2021.00406
– ident: ref16
  doi: 10.1109/ICCV.2019.00925
– ident: ref153
  doi: 10.1007/978-1-4899-7502-7_79-1
– ident: ref55
  doi: 10.1007/978-3-030-01270-0_31
– ident: ref27
  doi: 10.1109/CVPR42600.2020.01229
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref95
  article-title: On the information bottleneck theory of deep learning
– start-page: 109
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref2
  article-title: Efficient inference in fully connected CRFs with Gaussian edge potentials
– start-page: 15908
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref170
  article-title: Transformer in transformer
– ident: ref73
  doi: 10.1109/CVPR46437.2021.01549
– start-page: 6582
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref39
  article-title: Weakly supervised instance segmentation using the bounding box tightness prior
– ident: ref66
  doi: 10.1109/34.868688
– ident: ref19
  doi: 10.1007/s11263-021-01465-9
– start-page: 1
  volume-title: Proc. Brit. Mach. Vis. Conf.
  ident: ref137
  article-title: Semi-supervised semantic segmentation needs strong, high-dimensional perturbations
– ident: ref58
  doi: 10.1007/s11263-014-0733-5
– ident: ref68
  doi: 10.5555/3524938.3525087
– ident: ref36
  doi: 10.1109/CVPR.2016.344
– ident: ref79
  doi: 10.1109/CVPR52688.2022.01378
– ident: ref157
  doi: 10.1109/CVPR.2019.00976
– ident: ref123
  doi: 10.1109/CVPR.2014.49
– ident: ref164
  doi: 10.1109/CVPR52688.2022.01760
– start-page: 547
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref46
  article-title: Self-erasing network for integral object attention
– ident: ref4
  doi: 10.1109/CVPR.2019.00963
– ident: ref25
  doi: 10.1109/CVPR52688.2022.01378
– ident: ref41
  doi: 10.1109/CVPR.2019.00710
– ident: ref112
  doi: 10.1109/CVPR.2018.00195
– ident: ref129
  doi: 10.1109/ICCV.2003.1238308
– ident: ref184
  doi: 10.1109/CVPR42600.2020.00434
– ident: ref48
  doi: 10.1609/aaai.v34i07.6705
– ident: ref124
  doi: 10.1109/TPAMI.2016.2537320
– start-page: 8748
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref158
  article-title: Learning transferable visual models from natural language supervision
– ident: ref59
  doi: 10.1109/CVPR.2016.350
– ident: ref167
  doi: 10.48550/arXiv.2010.11929
– ident: ref118
  doi: 10.1109/CVPR.2017.326
– ident: ref128
  doi: 10.1109/CVPR46437.2021.01009
– ident: ref109
  doi: 10.1109/CVPR.2018.00147
– ident: ref28
  doi: 10.1109/CVPR52688.2022.00263
– ident: ref65
  doi: 10.1109/CVPR46437.2021.01652
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref7
  article-title: Multi-scale context aggregation by dilated convolutions
– ident: ref31
  doi: 10.1109/CVPR46437.2021.00126
– ident: ref84
  doi: 10.1109/ICCV.2019.00216
SSID ssj0014503
Score 2.5954344
SourceID crossref
SourceType Enrichment Source
Index Database
StartPage 9284
Title A Survey on Label-Efficient Deep Image Segmentation: Bridging the Gap Between Weak Supervision and Dense Prediction
Volume 45
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/eLvHCXMwtV1Lb9NAEF6FwgEOPAoVBYr2wC1y8du73FJoaaVSVSLQiIu1tscQkbhWEkflr_JrmFmvH4SH6IHLKlp5J7bn8-zO7sw3jL2IRBC5mfAsO8fGz8C20LPFDy8F4eW4Ys50SZaPp9HZmZhM5Plg8L3JhVnPoqIQV1ey_K-qxj5UNqXOXkPdrVDswN-odGxR7dj-k-JHaAwWa_zUUa-nKoGZdahpIujQ_w1AOTyZU5zOe_g8N3lHOrjjgDK3mtypt6ocHpgIrgtQX1FkSUZl2QUvF0ug-I1smraqNWtc8h-p9ERTh1wfSJSax5MGGxIUkjLXkZygOSsaXtB2y8ekjVzAtDPftWH6RDn03UlA3Tmp4Es13ew9rtS3qr-z4XptXF272RkiaIRJHgfd5zohosmVP1nwmpDSIFX0zLF06_pzZmqXnk7x_s20oVlXx-ejdyf7dCf7HtHs2W43STaBARtzZxvRqH0pW8ZaRkwyYiPjBrvpRoGUdW5he8LlB7pqd_uMTUKXLV_-eh-9RVNv9TO-z-4at4WParg9YAMottm9piQINzPENrvT47d8yJYjXmORXxZ8A4ucsMg1Fnkfi694g0SOSOSIRG6QyAmJvIdEjhjiGom8Q-Ij9uHocPz62DJVPqwUn31loU0QOSgHX4JS6JCgCxH6yk5VBEJFNjiuK4JE2B6qHkSO6-Ekl6HMiQcqoQE7bKu4LOAx48S67svIDYmXTwqhhB944CRZkuKfBPkuc5rXGKeGAp8qscziP6tvlw3bMWVNAPOXq59c6-qn7HaH-2dsa7WoYI_dSter6XLxXOPlB_rtpEg
linkProvider IEEE
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=A+Survey+on+Label-Efficient+Deep+Image+Segmentation%3A+Bridging+the+Gap+Between+Weak+Supervision+and+Dense+Prediction&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Shen%2C+Wei&rft.au=Peng%2C+Zelin&rft.au=Wang%2C+Xuehui&rft.au=Wang%2C+Huayu&rft.date=2023-08-01&rft.issn=0162-8828&rft.eissn=2160-9292&rft.volume=45&rft.issue=8&rft.spage=9284&rft.epage=9305&rft_id=info:doi/10.1109%2FTPAMI.2023.3246102&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TPAMI_2023_3246102
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