Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation

Environment perception in autonomous driving vehicles often heavily relies on deep neural networks (DNNs), which are subject to domain shifts, leading to a significantly decreased performance during DNN deployment. Usually, this problem is addressed by unsupervised domain adaptation (UDA) approaches...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on intelligent transportation systems Ročník 23; číslo 11; s. 20899 - 20911
Hlavní autoři: Klingner, Marvin, Ayache, Mouadh, Fingscheidt, Tim
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.11.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:1524-9050, 1558-0016
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Environment perception in autonomous driving vehicles often heavily relies on deep neural networks (DNNs), which are subject to domain shifts, leading to a significantly decreased performance during DNN deployment. Usually, this problem is addressed by unsupervised domain adaptation (UDA) approaches trained either simultaneously on source and target domain datasets or even source-free only on target data in an offline fashion. In this work, we further expand a source-free UDA approach to a continual and therefore online-capable UDA on a single-image basis for semantic segmentation. Accordingly, our method only requires the pre-trained model from the supplier (trained in the source domain) and the current (unlabeled target domain) camera image. Our method Continual BatchNorm Adaptation (CBNA) modifies the source domain statistics in the batch normalization layers, using target domain images in an unsupervised fashion, which yields consistent performance improvements during inference. Thereby, in contrast to existing works, our approach can be applied to improve a DNN continuously on a single-image basis during deployment without access to source data, without algorithmic delay, and nearly without computational overhead. We show the consistent effectiveness of our method across a wide variety of source/target domain settings for semantic segmentation. Code is available at https://github.com/ifnspaml/CBNA
AbstractList Environment perception in autonomous driving vehicles often heavily relies on deep neural networks (DNNs), which are subject to domain shifts, leading to a significantly decreased performance during DNN deployment. Usually, this problem is addressed by unsupervised domain adaptation (UDA) approaches trained either simultaneously on source and target domain datasets or even source-free only on target data in an offline fashion. In this work, we further expand a source-free UDA approach to a continual and therefore online-capable UDA on a single-image basis for semantic segmentation. Accordingly, our method only requires the pre-trained model from the supplier (trained in the source domain) and the current (unlabeled target domain) camera image. Our method Continual BatchNorm Adaptation (CBNA) modifies the source domain statistics in the batch normalization layers, using target domain images in an unsupervised fashion, which yields consistent performance improvements during inference. Thereby, in contrast to existing works, our approach can be applied to improve a DNN continuously on a single-image basis during deployment without access to source data, without algorithmic delay, and nearly without computational overhead. We show the consistent effectiveness of our method across a wide variety of source/target domain settings for semantic segmentation. Code is available at https://github.com/ifnspaml/CBNA
Author Klingner, Marvin
Fingscheidt, Tim
Ayache, Mouadh
Author_xml – sequence: 1
  givenname: Marvin
  orcidid: 0000-0001-7675-750X
  surname: Klingner
  fullname: Klingner, Marvin
  email: m.klingner@tu-bs.de
  organization: Institute of Communications Technology, Technische Universität Braunschweig, Braunschweig, Germany
– sequence: 2
  givenname: Mouadh
  surname: Ayache
  fullname: Ayache, Mouadh
  email: m.ayache@tu-bs.de
  organization: Institute of Communications Technology, Technische Universität Braunschweig, Braunschweig, Germany
– sequence: 3
  givenname: Tim
  orcidid: 0000-0002-8895-5041
  surname: Fingscheidt
  fullname: Fingscheidt, Tim
  email: t.fingscheidt@tu-bs.de
  organization: Institute of Communications Technology, Technische Universität Braunschweig, Braunschweig, Germany
BookMark eNp9kD9PwzAQxS1UJNrCB0AskVhgSLF9thNPqI34U6kqQ8tsOYkDqRq7OOnAt8dRKgYGpnt3-r2705ugkXXWIHRN8IwQLB-2y-1mRjGlMyASUwFnaEw4T2OMiRj1mrJYYo4v0KRtd2HKOCFj9Jg529X2qPfRQnfF59r5JpqX-tDprnY2ussW6_l9VDkfbUyjA1sE8dEYOwCX6LzS-9ZcneoUvT8_bbPXePX2sszmq7gAEF2cSwIUGKalEWWeJ4SXAGkFRpuca6FLWUpqTE5laAoqU8Z4LmiSFkJwTQGm6HbYe_Du62jaTu3c0dtwUtEEGKQJYBaoZKAK79rWm0oV9fBn53W9VwSrPi3Vp6X6tNQpreAkf5wHXzfaf__ruRk8tTHmlw-_Q8pT-AHIInX6
CODEN ITISFG
CitedBy_id crossref_primary_10_1038_s41598_025_05648_z
crossref_primary_10_1016_j_microc_2025_113384
crossref_primary_10_1016_j_suscom_2024_100984
crossref_primary_10_1109_TPAMI_2024_3446949
crossref_primary_10_1109_ACCESS_2023_3277785
crossref_primary_10_1016_j_eswa_2023_122120
Cites_doi 10.1007/s11263-015-0816-y
10.1109/CVPR42600.2020.00637
10.1007/978-3-030-58555-6_42
10.1109/TPAMI.2017.2699184
10.1007/978-3-030-58574-7_25
10.1109/ICCV.2019.00153
10.1109/CVPR.2018.00352
10.1007/978-3-030-01225-0_29
10.1109/ICCV48922.2021.00696
10.1109/ITSC48978.2021.9564566
10.1109/ACCESS.2019.2949697
10.1109/CVPR.2019.00963
10.1109/ICCV.2015.169
10.1007/978-3-030-58598-3_44
10.1109/ICRA.2018.8460982
10.1109/CVPR.2019.00710
10.1109/CVPR.2016.350
10.1109/ICCV.2019.00393
10.1109/CVPR.2019.00258
10.1016/j.patcog.2021.108292
10.1177/0278364913491297
10.1109/CVPR.2016.352
10.1109/CVPR.2017.700
10.1007/978-3-030-58542-6_18
10.1109/CVPR46437.2021.00824
10.1186/s40537-016-0043-6
10.1007/978-3-030-58583-9_29
10.1109/CVPR42600.2020.01265
10.1109/ICCVW54120.2021.00202
10.1109/ICCV.2019.00107
10.1109/CVPR.2015.7298925
10.1007/978-3-030-01219-9_18
10.1109/ICCV.2019.00746
10.1007/s11263-014-0733-5
10.1007/978-3-319-46475-6_7
10.1109/CVPR42600.2020.00966
10.1016/j.patcog.2018.03.005
10.1109/CVPR.2015.7298965
10.1109/CVPR.2016.90
10.1109/WACV48630.2021.00052
10.1109/CVPR.2019.00262
10.1109/CVPR46437.2021.00127
10.1109/CVPR42600.2020.00382
10.1109/ICCV.2017.534
10.1109/CVPR42600.2020.01299
10.1109/ICCV.2019.00219
10.1109/WACVW54805.2022.00027
10.1109/CVPR46437.2021.01141
10.1109/CVPR.2018.00780
10.1109/CVPRW.2019.00181
10.1007/978-3-030-58542-6_5
10.1109/CVPR42600.2020.00414
10.1109/ICCV.2019.00693
10.1109/ICCV.2019.00218
10.1109/ICCV48922.2021.01005
10.1109/WACV48630.2021.00066
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
ESBDL
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
FR3
JQ2
KR7
L7M
L~C
L~D
DOI 10.1109/TITS.2022.3190263
DatabaseName IEEE Xplore (IEEE)
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE/IET Electronic Library (IEL) (UW System Shared)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
Engineering Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Civil Engineering Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Civil Engineering Abstracts

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-0016
EndPage 20911
ExternalDocumentID 10_1109_TITS_2022_3190263
9843858
Genre orig-research
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AIBXA
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
ESBDL
HZ~
H~9
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
ZY4
AAYXX
CITATION
7SC
7SP
8FD
FR3
JQ2
KR7
L7M
L~C
L~D
ID FETCH-LOGICAL-c336t-b91323402de6dbb715d338f3eaeb5a6ad9d92eeb29a6ac298445b6278c665a233
IEDL.DBID RIE
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000833052800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1524-9050
IngestDate Sun Nov 30 04:55:23 EST 2025
Sat Nov 29 06:35:01 EST 2025
Tue Nov 18 21:52:55 EST 2025
Wed Aug 27 02:18:56 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 11
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c336t-b91323402de6dbb715d338f3eaeb5a6ad9d92eeb29a6ac298445b6278c665a233
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-8895-5041
0000-0001-7675-750X
OpenAccessLink https://ieeexplore.ieee.org/document/9843858
PQID 2734387304
PQPubID 75735
PageCount 13
ParticipantIDs ieee_primary_9843858
crossref_primary_10_1109_TITS_2022_3190263
crossref_citationtrail_10_1109_TITS_2022_3190263
proquest_journals_2734387304
PublicationCentury 2000
PublicationDate 2022-11-01
PublicationDateYYYYMMDD 2022-11-01
PublicationDate_xml – month: 11
  year: 2022
  text: 2022-11-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on intelligent transportation systems
PublicationTitleAbbrev TITS
PublicationYear 2022
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref56
ref12
ref59
ref58
ref14
ref53
ref55
ref10
ref17
ref16
fleuret (ref54) 2021
ref19
ref18
li (ref49) 2020
kingma (ref65) 2015
ref51
ref50
ronneberger (ref72) 2015
ref46
ref45
ref48
ref42
ref41
ref44
ref43
ref8
hoffman (ref34) 2016
ref7
ref9
ref4
ref6
paszke (ref64) 2016
ref5
ref40
ref35
liang (ref52) 2020
ref37
ref36
ref31
ref30
ref33
ref32
stan (ref47) 2020
yu (ref61) 2018
ref2
ref1
ref38
dou (ref26) 2019
eigen (ref3) 2014
ref71
ref70
ref73
ref68
ref24
ref23
ioffe (ref57) 2015
ref69
ref25
ref20
ref66
lee (ref67) 2019
ref21
ref28
ref27
li (ref22) 2017
ref29
ganin (ref11) 2015
zhang (ref15) 2022; 122
ref60
simonyan (ref63) 2015
ref62
hoffman (ref39) 2018
References_xml – ident: ref71
  doi: 10.1007/s11263-015-0816-y
– ident: ref51
  doi: 10.1109/CVPR42600.2020.00637
– ident: ref35
  doi: 10.1007/978-3-030-58555-6_42
– ident: ref2
  doi: 10.1109/TPAMI.2017.2699184
– ident: ref42
  doi: 10.1007/978-3-030-58574-7_25
– start-page: 2366
  year: 2014
  ident: ref3
  article-title: Depth map prediction from a single image using a multi-scale deep network
  publication-title: Proc Adv Neural Inf Process Syst
– start-page: 448
  year: 2015
  ident: ref57
  article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift
  publication-title: Proc Int Conf Mach Learn
– ident: ref27
  doi: 10.1109/ICCV.2019.00153
– ident: ref8
  doi: 10.1109/CVPR.2018.00352
– start-page: 1
  year: 2015
  ident: ref63
  article-title: Very deep convolutional networks for large-scale image recognition
  publication-title: Proc ICLR
– ident: ref25
  doi: 10.1007/978-3-030-01225-0_29
– ident: ref55
  doi: 10.1109/ICCV48922.2021.00696
– ident: ref48
  doi: 10.1109/ITSC48978.2021.9564566
– start-page: 6447
  year: 2019
  ident: ref26
  article-title: Domain generalization via model-agnostic learning of semantic features
  publication-title: Proc NeurIPS
– year: 2018
  ident: ref61
  article-title: BDD100 K: A diverse driving video database with scalable annotation tooling
  publication-title: arXiv 1805 04687
– start-page: 1
  year: 2017
  ident: ref22
  article-title: Revisiting batch normalization for practical domain adaptation
  publication-title: Proc ICLR
– ident: ref37
  doi: 10.1109/ACCESS.2019.2949697
– start-page: 1
  year: 2015
  ident: ref65
  article-title: Adam: A method for stochastic optimization
  publication-title: Proc ICLR
– ident: ref6
  doi: 10.1109/CVPR.2019.00963
– ident: ref7
  doi: 10.1109/ICCV.2015.169
– ident: ref32
  doi: 10.1007/978-3-030-58598-3_44
– start-page: 1180
  year: 2015
  ident: ref11
  article-title: Unsupervised domain adaptation by backpropagation
  publication-title: Proc ICML
– ident: ref46
  doi: 10.1109/ICRA.2018.8460982
– ident: ref17
  doi: 10.1109/CVPR.2019.00710
– start-page: 1989
  year: 2018
  ident: ref39
  article-title: CyCADA: Cycle-consistent adversarial domain adaptation
  publication-title: Proc ICML
– ident: ref10
  doi: 10.1109/CVPR.2016.350
– year: 2016
  ident: ref34
  article-title: FCNs in the wild: Pixel-level adversarial and constraint-based adaptation
  publication-title: arXiv 1612 02649
– ident: ref73
  doi: 10.1109/ICCV.2019.00393
– ident: ref38
  doi: 10.1109/CVPR.2019.00258
– volume: 122
  year: 2022
  ident: ref15
  article-title: Generalizable semantic segmentation via model-agnostic learning and target-specific normalization
  publication-title: Pattern Recognit
  doi: 10.1016/j.patcog.2021.108292
– ident: ref9
  doi: 10.1177/0278364913491297
– ident: ref59
  doi: 10.1109/CVPR.2016.352
– ident: ref4
  doi: 10.1109/CVPR.2017.700
– ident: ref43
  doi: 10.1007/978-3-030-58542-6_18
– ident: ref20
  doi: 10.1109/CVPR46437.2021.00824
– ident: ref13
  doi: 10.1186/s40537-016-0043-6
– ident: ref70
  doi: 10.1007/978-3-030-58583-9_29
– ident: ref18
  doi: 10.1109/CVPR42600.2020.01265
– ident: ref21
  doi: 10.1109/ICCVW54120.2021.00202
– start-page: 9613
  year: 2021
  ident: ref54
  article-title: Uncertainty reduction for model adaptation in semantic segmentation
  publication-title: Proc IEEE/CVF Conf Comput Vis Pattern Recognit (CVPR)
– ident: ref33
  doi: 10.1109/ICCV.2019.00107
– ident: ref60
  doi: 10.1109/CVPR.2015.7298925
– start-page: 6028
  year: 2020
  ident: ref52
  article-title: Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation
  publication-title: Proc ICML
– ident: ref44
  doi: 10.1007/978-3-030-01219-9_18
– ident: ref68
  doi: 10.1109/ICCV.2019.00746
– ident: ref66
  doi: 10.1007/s11263-014-0733-5
– ident: ref58
  doi: 10.1007/978-3-319-46475-6_7
– ident: ref53
  doi: 10.1109/CVPR42600.2020.00966
– year: 2020
  ident: ref49
  article-title: A free lunch for unsupervised domain adaptive object detection without source data
  publication-title: arXiv 2012 05400
– start-page: 1
  year: 2019
  ident: ref67
  article-title: SPIGAN: Privileged adversarial learning from simulation
  publication-title: Proc ICLR
– ident: ref23
  doi: 10.1016/j.patcog.2018.03.005
– ident: ref1
  doi: 10.1109/CVPR.2015.7298965
– ident: ref5
  doi: 10.1109/CVPR.2016.90
– ident: ref50
  doi: 10.1109/WACV48630.2021.00052
– year: 2020
  ident: ref47
  article-title: Unsupervised model adaptation for continual semantic segmentation
  publication-title: arXiv 2009 12518
– ident: ref36
  doi: 10.1109/CVPR.2019.00262
– ident: ref56
  doi: 10.1109/CVPR46437.2021.00127
– year: 2016
  ident: ref64
  article-title: ENet: A deep neural network architecture for real-time semantic segmentation
  publication-title: ArXiv 1606 02147
– ident: ref16
  doi: 10.1109/CVPR42600.2020.00382
– ident: ref62
  doi: 10.1109/ICCV.2017.534
– ident: ref69
  doi: 10.1109/CVPR42600.2020.01299
– ident: ref14
  doi: 10.1109/ICCV.2019.00219
– start-page: 234
  year: 2015
  ident: ref72
  article-title: U-Net: Convolutional networks for biomedical image segmentation
  publication-title: Proc Int Conf Med Image Comput Comput -Assist Intervent
– ident: ref19
  doi: 10.1109/WACVW54805.2022.00027
– ident: ref29
  doi: 10.1109/CVPR46437.2021.01141
– ident: ref12
  doi: 10.1109/CVPR.2018.00780
– ident: ref30
  doi: 10.1109/CVPRW.2019.00181
– ident: ref28
  doi: 10.1007/978-3-030-58542-6_5
– ident: ref40
  doi: 10.1109/CVPR42600.2020.00414
– ident: ref41
  doi: 10.1109/ICCV.2019.00693
– ident: ref31
  doi: 10.1109/ICCV.2019.00218
– ident: ref24
  doi: 10.1109/ICCV48922.2021.01005
– ident: ref45
  doi: 10.1109/WACV48630.2021.00066
SSID ssj0014511
Score 2.466021
Snippet Environment perception in autonomous driving vehicles often heavily relies on deep neural networks (DNNs), which are subject to domain shifts, leading to a...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 20899
SubjectTerms Adaptation
Adaptation models
Artificial neural networks
batch normalization
Data models
deep learning
Delays
Domain adaptation
Domains
Image segmentation
Neural networks
Semantic segmentation
Semantics
Task analysis
unsupervised learning
Title Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation
URI https://ieeexplore.ieee.org/document/9843858
https://www.proquest.com/docview/2734387304
Volume 23
WOSCitedRecordID wos000833052800001&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/IET Electronic Library (IEL) (UW System Shared)
  customDbUrl:
  eissn: 1558-0016
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014511
  issn: 1524-9050
  databaseCode: RIE
  dateStart: 20000101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD5swwd98DbF6ZQ--KBiXJv0lieZw6EgRdiEvZU0yXTgLuzi7_ck7YqiCL6lkJTwpT35vp6eLwDnXiAE7ro-Ea5mxA89RWJfRQSDZSwjOWRBZi3zn6IkiQcD_lyB67IWRmttfz7TN6Zpc_lqKlfmU1mLx77JY1WhGkVRXqtVZgyMz5b1RqU-4W6wzmB6Lm_1H_s9VIKUokDlqDnYtz3IHqryIxLb7aW787-J7cJ2QSOddr7ue1DRk33Y-mIuWIdbYzw1Mo6jzh3G27cE2anTVmKWJ9-di85d0r50kLQ6PT1GgEcSG6_johhpcgAv3ft-54EUxyUQyVi4JBlHZclQDyodqiyLvECh_hwyLXQWiFAorjjVqKQ5XkiKc_aDLKRRLMMwEJSxQ6hNphN9BI6kNJOe5FrL2KcKWTjyNMEUcklkLC5vgLsGMJWFl7g50uI9tZrC5anBPDWYpwXmDbgqh8xyI42_OtcNyGXHAt8GNNerlBav2iI1_jwsxkDlH_8-6gQ2zb3zAsIm1JbzlT6FDfmxHC3mZ_Yp-gQn68I7
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dS8MwFL3MKagPfovTqX3wQcW6Nkk_8iRTFIezCJvgW0iTTAc6ZZv-fm_SbiiK4FsKCQ0n7c05vb0nAAdhJCXuusyXgaE-i0Ptp0wnPgbLVCWqR6PcWea3kyxLHx74XQVOprUwxhj385k5tU2Xy9ev6t1-KmvwlNk81gzMRoyRsKjWmuYMrNOWc0clzOdBNMlhhgFvdFvdDmpBQlCiclQd9Nsu5I5V-RGL3QZztfy_qa3AUkkkvWax8qtQMYM1WPxiL7gOZ9Z6qm89R71zjLhPGfJTr6nlW5F-9w4vzrPmkYe01euYF4S4r7Dx-FKWIw024P7qsntx7ZcHJviK0njs5xy1JUVFqE2s8zwJI40KtEeNNHkkY6m55sSgluZ4oQjOmUV5TJJUxXEkCaWbUB28DswWeIqQXIWKG6NSRjTycGRqkmpkk8hZAl6DYAKgUKWbuD3U4lk4VRFwYTEXFnNRYl6D4-mQt8JK46_O6xbkaccS3xrUJ6skypdtJKxDD00xVLHt30ftw_x197Yt2q3sZgcW7H2KcsI6VMfDd7MLc-pj3B8N99wT9Qlwe8WC
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=Continual+BatchNorm+Adaptation+%28CBNA%29+for+Semantic+Segmentation&rft.jtitle=IEEE+transactions+on+intelligent+transportation+systems&rft.au=Klingner%2C+Marvin&rft.au=Ayache%2C+Mouadh&rft.au=Fingscheidt%2C+Tim&rft.date=2022-11-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1524-9050&rft.eissn=1558-0016&rft.volume=23&rft.issue=11&rft.spage=20899&rft_id=info:doi/10.1109%2FTITS.2022.3190263&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1524-9050&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1524-9050&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1524-9050&client=summon