Semi-Supervised Image Deraining Using Knowledge Distillation

Image deraining has achieved considerable progress based on supervised learning with synthetic training pairs, but is usually limited in handling real-world rainy images. Although semi-supervised methods are suggested to exploit real-world rainy images when training deep deraining models, their perf...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on circuits and systems for video technology Ročník 32; číslo 12; s. 8327 - 8341
Hlavní autori: Cui, Xin, Wang, Cong, Ren, Dongwei, Chen, Yunjin, Zhu, Pengfei
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.12.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:1051-8215, 1558-2205
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Image deraining has achieved considerable progress based on supervised learning with synthetic training pairs, but is usually limited in handling real-world rainy images. Although semi-supervised methods are suggested to exploit real-world rainy images when training deep deraining models, their performances are still notably inferior. To address this crucial issue, this work proposes a semi-supervised image deraining network with knowledge distillation (SSID-KD) for better exploiting real-world rainy images. In particular, the consistency of feature distribution of rain streaks extracted from synthetic and real-world rainy images is enforced by adopting knowledge distillation. Moreover, as for the backbone in SSID-KD, we propose the multi-scale feature fusion module and the pyramid fusion module to better extract deep features of rainy images. SSID-KD can relieve the problem of over-deraining or under-deraining for real-world rainy images, while it can keep comparable performance with supervised deraining methods on several benchmark datasets. Extensive experiments on both synthetic and real-world rainy images have validated that our SSID-KD not only can achieve better deraining results than existing semi-supervised deraining methods but also are quantitatively comparable with state-of-the-art supervised deraining methods. Benefiting from the well exploration of real-world rainy images, our SSID-KD can obtain more visually plausible deraining results. The source code and trained models are publicly available at https://github.com/cuiyixin555/SSID-KD .
AbstractList Image deraining has achieved considerable progress based on supervised learning with synthetic training pairs, but is usually limited in handling real-world rainy images. Although semi-supervised methods are suggested to exploit real-world rainy images when training deep deraining models, their performances are still notably inferior. To address this crucial issue, this work proposes a semi-supervised image deraining network with knowledge distillation (SSID-KD) for better exploiting real-world rainy images. In particular, the consistency of feature distribution of rain streaks extracted from synthetic and real-world rainy images is enforced by adopting knowledge distillation. Moreover, as for the backbone in SSID-KD, we propose the multi-scale feature fusion module and the pyramid fusion module to better extract deep features of rainy images. SSID-KD can relieve the problem of over-deraining or under-deraining for real-world rainy images, while it can keep comparable performance with supervised deraining methods on several benchmark datasets. Extensive experiments on both synthetic and real-world rainy images have validated that our SSID-KD not only can achieve better deraining results than existing semi-supervised deraining methods but also are quantitatively comparable with state-of-the-art supervised deraining methods. Benefiting from the well exploration of real-world rainy images, our SSID-KD can obtain more visually plausible deraining results. The source code and trained models are publicly available at https://github.com/cuiyixin555/SSID-KD .
Author Chen, Yunjin
Ren, Dongwei
Zhu, Pengfei
Cui, Xin
Wang, Cong
Author_xml – sequence: 1
  givenname: Xin
  orcidid: 0000-0002-7088-3799
  surname: Cui
  fullname: Cui, Xin
  email: 2019216101@tju.edu.cn
  organization: College of Intelligence and Computing, Tianjin University, Tianjin, China
– sequence: 2
  givenname: Cong
  surname: Wang
  fullname: Wang, Cong
  email: supercong94@gmail.com
  organization: Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong
– sequence: 3
  givenname: Dongwei
  orcidid: 0000-0002-0965-6810
  surname: Ren
  fullname: Ren, Dongwei
  email: rendongweihit@gmail.com
  organization: School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
– sequence: 4
  givenname: Yunjin
  orcidid: 0000-0002-4428-2797
  surname: Chen
  fullname: Chen, Yunjin
  email: chenyunjin_nudt@hotmail.com
  organization: Alibaba Cloud, Hangzhou, China
– sequence: 5
  givenname: Pengfei
  orcidid: 0000-0002-4310-9140
  surname: Zhu
  fullname: Zhu, Pengfei
  email: zhupengfei@tju.edu.cn
  organization: College of Intelligence and Computing, Tianjin University, Tianjin, China
BookMark eNp9kE1PwzAMhiM0JMbgD8BlEueOxE2WROKCxtfEJA7buEZp606ZunYkHYh_T7pNHDhwsS3brz-ec9KrmxoJuWJ0xBjVt4vJ_H0xAgowSpmmgo1PSJ8JoRIAKnoxjrlEARNn5DyENaWMKy775G6OG5fMd1v0ny5gMZxu7AqHD-itq129Gi5DZ1_r5qvCoqu40Lqqsq1r6gtyWtoq4OXRD8jy6XExeUlmb8_Tyf0syUGLNikoUKkYIBdpFsOCZzLPhMacS8tYpi3YVMk8FTniON7LS8XBiiyTqS4FTQfk5jB365uPHYbWrJudr-NKA5LLMWOgIHbBoSv3TQgeS7P1bmP9t2HUdJTMnpLpKJkjpShSf0S5a_fPtZFA9b_0-iB1iPi7SyvQirP0Bwp7dig
CODEN ITCTEM
CitedBy_id crossref_primary_10_1016_j_patcog_2023_109740
crossref_primary_10_1109_TCSVT_2023_3327113
crossref_primary_10_1109_ACCESS_2023_3325842
crossref_primary_10_1109_TIM_2023_3330222
crossref_primary_10_1109_TMC_2024_3470328
crossref_primary_10_1109_TCI_2025_3527142
crossref_primary_10_1007_s13042_025_02744_4
crossref_primary_10_1109_TCSVT_2024_3411655
crossref_primary_10_1364_OE_551682
crossref_primary_10_1109_TCSVT_2023_3318304
crossref_primary_10_1109_TCSVT_2025_3526647
crossref_primary_10_1007_s00530_023_01156_0
crossref_primary_10_1016_j_image_2025_117311
crossref_primary_10_1109_ACCESS_2025_3555632
crossref_primary_10_1109_TCSVT_2024_3400368
crossref_primary_10_3390_app15084325
crossref_primary_10_1007_s00371_024_03565_2
crossref_primary_10_1007_s00530_024_01348_2
crossref_primary_10_1016_j_eswa_2025_127670
crossref_primary_10_1109_TCSVT_2022_3222013
crossref_primary_10_1109_TCSVT_2023_3285213
crossref_primary_10_1007_s11227_024_06665_x
crossref_primary_10_1109_TITS_2024_3503556
crossref_primary_10_1109_TMM_2024_3366765
crossref_primary_10_1016_j_ins_2024_120107
crossref_primary_10_1007_s00521_023_08899_x
crossref_primary_10_1117_1_JEI_33_4_043003
crossref_primary_10_1016_j_patcog_2025_111777
crossref_primary_10_1109_TNNLS_2023_3243666
crossref_primary_10_1109_TCSVT_2023_3246953
crossref_primary_10_1016_j_cviu_2024_104118
crossref_primary_10_1016_j_knosys_2023_111116
crossref_primary_10_1088_1361_6501_adcc45
crossref_primary_10_1016_j_engappai_2024_109207
crossref_primary_10_1109_TCE_2025_3534680
crossref_primary_10_3390_app14167022
crossref_primary_10_1007_s11042_024_19006_0
crossref_primary_10_1109_ACCESS_2024_3499957
crossref_primary_10_1016_j_neunet_2024_106428
crossref_primary_10_1109_TITS_2022_3208372
crossref_primary_10_1109_TRPMS_2025_3541169
crossref_primary_10_1109_TCSVT_2023_3323128
crossref_primary_10_1109_TITS_2025_3548157
Cites_doi 10.1109/CVPR.2018.00341
10.1109/ICCV.2017.189
10.1109/TPAMI.2016.2551244
10.1109/TIP.2020.2990606
10.1109/ICME46284.2020.9102878
10.1109/ICCV.2015.388
10.1007/978-3-030-89370-5_20
10.1109/CVPR.2017.301
10.1145/3240508.3240636
10.1109/TPAMI.2010.168
10.1109/TIP.2011.2179057
10.1109/CVPR.2018.00853
10.1109/TCSVT.2019.2920407
10.1109/TIP.2017.2691802
10.1109/CVPR42600.2020.00340
10.1145/3394171.3413820
10.1016/0167-2789(92)90242-F
10.1109/ICASSP40776.2020.9053081
10.1109/WACV45572.2020.9093393
10.1109/TNNLS.2019.2926481
10.1109/TIP.2018.2880512
10.1109/CVPR.2019.00406
10.1109/CVPR.2017.183
10.1145/3394171.3413559
10.1109/CVPR42600.2020.00223
10.1109/CVPR46437.2021.01458
10.1109/CVPR42600.2020.00837
10.1109/TIP.2003.819861
10.1109/TIP.2019.2952690
10.1109/CVPR.2017.549
10.1109/TIP.2018.2811546
10.1016/j.neunet.2019.08.022
10.1109/CVPR42600.2020.00280
10.1109/CVPR.2019.00400
10.1109/CVPR.2004.1315077
10.1109/TCSVT.2020.3022707
10.1109/ICCV.2017.244
10.1145/3394171.3413554
10.1109/ICCV.2013.247
10.1109/TCSVT.2022.3153685
10.1145/3343031.3351149
10.1109/CVPR.2018.00658
10.1609/aaai.v33i01.33019332
10.1109/CVPR46437.2021.01212
10.1007/978-3-030-01234-2_16
10.1109/CVPR.2019.01255
10.1109/ICIP.2019.8803329
10.1109/CVPR42600.2020.00352
10.1109/TPAMI.2017.2753804
10.1109/TCSVT.2021.3063853
10.1109/ICIP.2013.6738189
10.1109/TCSVT.2020.2972566
10.1109/CVPR.2017.186
10.1109/LSP.2012.2227726
10.1109/TPAMI.2018.2873610
10.1016/j.knosys.2020.106595
10.1109/TCSVT.2020.3044887
10.1109/CVPR.2019.00860
10.1109/TIP.2020.2994443
10.1109/CVPR.2016.299
10.1109/CVPR42600.2020.00317
10.1109/TPAMI.2019.2926357
10.1109/TIP.2015.2428933
10.1109/ICIP.2019.8803308
10.1109/CVPR.2018.00079
10.1109/CVPR.2019.00176
10.1109/CVPR42600.2020.01457
10.1109/CVPR.2018.00695
10.1109/CVPR46437.2021.01455
10.3115/v1/D14-1179
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TCSVT.2022.3190516
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-2205
EndPage 8341
ExternalDocumentID 10_1109_TCSVT_2022_3190516
9829841
Genre orig-research
GrantInformation_xml – fundername: Alibaba Group through Alibaba Innovative Research Program
– fundername: National Natural Science Foundation of China
  grantid: 62172127
  funderid: 10.13039/501100001809
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
HZ~
H~9
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
RXW
TAE
TN5
VH1
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c295t-d0207812e453b207d4b7cb59ec47a11b9a2a387c35cee62054f842a5bb739f503
IEDL.DBID RIE
ISICitedReferencesCount 54
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000936985600020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1051-8215
IngestDate Sun Nov 30 04:34:28 EST 2025
Sat Nov 29 01:44:19 EST 2025
Tue Nov 18 22:44:20 EST 2025
Wed Aug 27 02:29:09 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 12
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-d0207812e453b207d4b7cb59ec47a11b9a2a387c35cee62054f842a5bb739f503
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-7088-3799
0000-0002-0965-6810
0000-0002-4428-2797
0000-0002-4310-9140
PQID 2747611282
PQPubID 85433
PageCount 15
ParticipantIDs crossref_primary_10_1109_TCSVT_2022_3190516
ieee_primary_9829841
proquest_journals_2747611282
crossref_citationtrail_10_1109_TCSVT_2022_3190516
PublicationCentury 2000
PublicationDate 2022-12-01
PublicationDateYYYYMMDD 2022-12-01
PublicationDate_xml – month: 12
  year: 2022
  text: 2022-12-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on circuits and systems for video technology
PublicationTitleAbbrev TCSVT
PublicationYear 2022
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref13
ref56
ref12
ref59
ref15
ref14
ref53
ref52
ref55
ref11
ref54
ref10
chen (ref75) 2020
ref17
ref16
ref19
ref18
paszke (ref73) 2017
ref51
ref50
ref46
ref45
ref48
ref47
ref42
ref41
ref44
ref49
ref8
ref7
kingma (ref76) 2015
ref9
ref4
ref3
ref6
ref5
ref40
ref80
ref35
ref34
ref37
ref36
ref31
ref74
ref33
ref32
ref2
zhu (ref58) 2017
ref1
ref39
ref38
fan (ref27) 2018
ref71
ref70
ref72
ref68
ref24
ref67
ref23
ref26
ref69
ref25
ref64
ref20
ref63
ref22
ref65
ref21
holger caesar (ref77) 2018
ref28
redmon (ref79) 2018
ref29
ref60
liu (ref30) 2018
he (ref43) 2011; 33
yu (ref78) 2020
ref62
ref61
wang (ref66) 2019
References_xml – ident: ref53
  doi: 10.1109/CVPR.2018.00341
– ident: ref12
  doi: 10.1109/ICCV.2017.189
– ident: ref45
  doi: 10.1109/TPAMI.2016.2551244
– ident: ref61
  doi: 10.1109/TIP.2020.2990606
– ident: ref24
  doi: 10.1109/ICME46284.2020.9102878
– ident: ref5
  doi: 10.1109/ICCV.2015.388
– ident: ref31
  doi: 10.1007/978-3-030-89370-5_20
– ident: ref13
  doi: 10.1109/CVPR.2017.301
– start-page: 1
  year: 2020
  ident: ref75
  article-title: Big self-supervised models are strong semi-supervised learners
  publication-title: Proc NeurIPS
– ident: ref60
  doi: 10.1145/3240508.3240636
– volume: 33
  start-page: 2341
  year: 2011
  ident: ref43
  article-title: Single image haze removal using dark channel prior
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2010.168
– start-page: 2526
  year: 2017
  ident: ref58
  article-title: Joint bilayer optimization for single-image rain streak removal
  publication-title: Proc IEEE ICIP
– ident: ref3
  doi: 10.1109/TIP.2011.2179057
– ident: ref28
  doi: 10.1109/CVPR.2018.00853
– ident: ref33
  doi: 10.1109/TCSVT.2019.2920407
– ident: ref56
  doi: 10.1109/TIP.2017.2691802
– ident: ref68
  doi: 10.1109/CVPR42600.2020.00340
– ident: ref19
  doi: 10.1145/3394171.3413820
– ident: ref74
  doi: 10.1016/0167-2789(92)90242-F
– start-page: 2
  year: 2018
  ident: ref27
  article-title: Residual-guide feature fusion network for single image deraining
  publication-title: Proc ACM MM
– year: 2018
  ident: ref79
  article-title: YOLOv3: An incremental improvement
  publication-title: arXiv 1804 02767
– ident: ref36
  doi: 10.1109/ICASSP40776.2020.9053081
– ident: ref62
  doi: 10.1109/WACV45572.2020.9093393
– ident: ref4
  doi: 10.1109/TNNLS.2019.2926481
– ident: ref7
  doi: 10.1109/TIP.2018.2880512
– ident: ref18
  doi: 10.1109/CVPR.2019.00406
– ident: ref15
  doi: 10.1109/CVPR.2017.183
– ident: ref17
  doi: 10.1145/3394171.3413559
– ident: ref69
  doi: 10.1109/CVPR42600.2020.00223
– ident: ref40
  doi: 10.1109/CVPR46437.2021.01458
– ident: ref65
  doi: 10.1109/CVPR42600.2020.00837
– ident: ref72
  doi: 10.1109/TIP.2003.819861
– ident: ref70
  doi: 10.1109/TIP.2019.2952690
– ident: ref80
  doi: 10.1109/CVPR.2017.549
– ident: ref11
  doi: 10.1109/TIP.2018.2811546
– ident: ref29
  doi: 10.1016/j.neunet.2019.08.022
– year: 2019
  ident: ref66
  article-title: A survey on rain removal from video and single image
  publication-title: arXiv 1909 08326
– ident: ref2
  doi: 10.1109/CVPR42600.2020.00280
– ident: ref1
  doi: 10.1109/CVPR.2019.00400
– ident: ref55
  doi: 10.1109/CVPR.2004.1315077
– ident: ref26
  doi: 10.1109/TCSVT.2020.3022707
– ident: ref42
  doi: 10.1109/ICCV.2017.244
– ident: ref38
  doi: 10.1145/3394171.3413554
– ident: ref9
  doi: 10.1109/ICCV.2013.247
– ident: ref22
  doi: 10.1109/TCSVT.2022.3153685
– ident: ref59
  doi: 10.1145/3343031.3351149
– ident: ref51
  doi: 10.1109/CVPR.2018.00658
– ident: ref41
  doi: 10.1609/aaai.v33i01.33019332
– ident: ref23
  doi: 10.1109/CVPR46437.2021.01212
– ident: ref25
  doi: 10.1007/978-3-030-01234-2_16
– ident: ref46
  doi: 10.1109/CVPR.2019.01255
– ident: ref47
  doi: 10.1109/ICIP.2019.8803329
– ident: ref71
  doi: 10.1109/CVPR42600.2020.00352
– ident: ref44
  doi: 10.1109/TPAMI.2017.2753804
– start-page: 1
  year: 2018
  ident: ref30
  article-title: Non-local recurrent network for image restoration
  publication-title: Proc NeurIPS
– ident: ref21
  doi: 10.1109/TCSVT.2021.3063853
– ident: ref57
  doi: 10.1109/ICIP.2013.6738189
– start-page: 6
  year: 2020
  ident: ref78
  article-title: BDD100K: A diverse driving video database with scalable annotation tooling
  publication-title: Proc IEEE CVPR
– ident: ref48
  doi: 10.1109/TCSVT.2020.2972566
– ident: ref14
  doi: 10.1109/CVPR.2017.186
– start-page: 1
  year: 2015
  ident: ref76
  article-title: Adam: A method for stochastic optimization
  publication-title: Proc ICLR
– ident: ref50
  doi: 10.1109/LSP.2012.2227726
– ident: ref32
  doi: 10.1109/TPAMI.2018.2873610
– ident: ref63
  doi: 10.1016/j.knosys.2020.106595
– start-page: 1
  year: 2017
  ident: ref73
  article-title: Automatic differentiation in pytorch
  publication-title: Proc NIPS Autodiff Workshop Future Gradient-Based Mach Learn Softw Techn
– start-page: 1209
  year: 2018
  ident: ref77
  article-title: COCO-Stuff: Thing and stuff classes in context
  publication-title: Proc IEEE CVPR
– ident: ref20
  doi: 10.1109/TCSVT.2020.3044887
– ident: ref35
  doi: 10.1109/CVPR.2019.00860
– ident: ref16
  doi: 10.1109/TIP.2020.2994443
– ident: ref8
  doi: 10.1109/CVPR.2016.299
– ident: ref37
  doi: 10.1109/CVPR42600.2020.00317
– ident: ref10
  doi: 10.1109/TPAMI.2019.2926357
– ident: ref6
  doi: 10.1109/TIP.2015.2428933
– ident: ref34
  doi: 10.1109/ICIP.2019.8803308
– ident: ref49
  doi: 10.1109/CVPR.2018.00079
– ident: ref54
  doi: 10.1109/CVPR.2019.00176
– ident: ref64
  doi: 10.1109/CVPR42600.2020.01457
– ident: ref52
  doi: 10.1109/CVPR.2018.00695
– ident: ref39
  doi: 10.1109/CVPR46437.2021.01455
– ident: ref67
  doi: 10.3115/v1/D14-1179
SSID ssj0014847
Score 2.5829415
Snippet Image deraining has achieved considerable progress based on supervised learning with synthetic training pairs, but is usually limited in handling real-world...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 8327
SubjectTerms Distillation
Feature extraction
knowledge distillation
Modules
Network architecture
semi-supervised learning
Semisupervised learning
Single image deraining
Source code
Supervised learning
Task analysis
Training
Title Semi-Supervised Image Deraining Using Knowledge Distillation
URI https://ieeexplore.ieee.org/document/9829841
https://www.proquest.com/docview/2747611282
Volume 32
WOSCitedRecordID wos000936985600020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-2205
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014847
  issn: 1051-8215
  databaseCode: RIE
  dateStart: 19910101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5q8aAHX1WsVtmDN43dTbKbBLxIa1GUIrRKb8smm4VCX_Th7zfJPlAUwVsOybJ8k8w3k8wD4EpiHrAkE0gyliKaGj_FWAkB0iH3M20IM1Kuuv4L6_f5aCRea3BT5cJorV3wmb61Q_eWn87Vxl6VtQXHgtss9S3GojxXq3oxoNw1EzPmQoC44bEyQcYX7WFn8D40riDGxkO19aiibyTkuqr8UMWOX3r7__uzA9gr7EjvPhf8IdT07Ah2v1QXbMDdQE_HaLBZWHWw0qn3NDXKw-vqoiuE58IFvOfyVs3r2vM-yYPjjuGt9zDsPKKiWQJSWIRrlBq7jxm21jQk0gxTKpmSodCKsiQIpEhwQjhTJDS0GGFjqWWc4iSUkhGRhT45gfpsPtOn4BFMGNOSZZIKmlIsA5mllEhpXCNtBNuEoEQvVkUlcdvQYhI7j8IXsUM8tojHBeJNuK7WLPI6Gn_ObliMq5kFvE1olUKKi6O2iq1bHRmrkeOz31edw479dh6D0oL6ernRF7CtPtbj1fLS7aJPZwTDOQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwED_GFNQHv6Y4ndoH3zSuTdMmAV_EOTY2h7AqeytNm8JgX-zDv98k_UBRBN_ykNByl9zvLrm7H8CNwMyhUcqRoDRBJFFxivISHCQ9ZqdSAaYfm-76fToYsNGIv1bgrqyFkVKa5DN5r4fmLT-Zxxt9VdbkDHOmq9S3NHNWXq1VvhkQZujElMPgIKaQrCiRsXkzeBq-ByoYxFjFqLojlf8Nhgyvyg9jbBCmffC_fzuE_dyTtB4z1R9BRc6OYe9Lf8EaPAzldIyGm4U2CCuZWN2pMh9WS-a8EJZJGLB6xb2a1dInfpKlx53AW_s5eOqgnC4BxZh7a5Qoz48qvJbEc4UaJkTQWHhcxoRGjiN4hCOX0dj1FDD6WPlqKSM48oSgLk892z2F6mw-k2dgudilVAqaCsJJQrBwRJoQVwgVHEml2jo4hfTCOO8lriktJqGJKWweGomHWuJhLvE63JZrFlknjT9n17SMy5m5eOvQKJQU5odtFerA2ld-I8Pnv6-6hp1O8NIP-91B7wJ29XeyjJQGVNfLjbyE7fhjPV4tr8yO-gTAU8aC
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=Semi-Supervised+Image+Deraining+Using+Knowledge+Distillation&rft.jtitle=IEEE+transactions+on+circuits+and+systems+for+video+technology&rft.au=Cui%2C+Xin&rft.au=Wang%2C+Cong&rft.au=Ren%2C+Dongwei&rft.au=Chen%2C+Yunjin&rft.date=2022-12-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1051-8215&rft.eissn=1558-2205&rft.volume=32&rft.issue=12&rft.spage=8327&rft_id=info:doi/10.1109%2FTCSVT.2022.3190516&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1051-8215&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1051-8215&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1051-8215&client=summon