Realistic Evaluation of Deep Active Learning for Image Classification and Semantic Segmentation

Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Recently, deep active learning has shown success on various tasks. However, the conventional evaluation schemes are either i...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	International journal of computer vision Ročník 133; číslo 7; s. 4294 - 4316
Hlavní autori:	Mittal, Sudhanshu, Niemeijer, Joshua, Çiçek, Özgün, Tatarchenko, Maxim, Ehrhardt, Jan, Schäfer, Jörg P., Handels, Heinz, Brox, Thomas
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York Springer US 01.07.2025 Springer Nature B.V
Predmet:	Artificial Intelligence Budgets Computer Imaging Computer Science Data augmentation Datasets German Conference on Pattern Recognition special issues (GCPR) Image annotation Image classification Image Processing and Computer Vision Image segmentation Labeling Machine learning Pattern Recognition Pattern Recognition and Graphics Redundancy Semantic segmentation Semantics Semi-supervised learning Vision Segmentation Active learning Semi supervised learning Classification
ISSN:	0920-5691, 1573-1405
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Recently, deep active learning has shown success on various tasks. However, the conventional evaluation schemes are either incomplete or below par. This study critically assesses various active learning approaches, identifying key factors essential for choosing the most effective active learning method. It includes a comprehensive guide to obtain the best performance for each case, in image classification and semantic segmentation. For image classification, the AL methods improve by a large-margin when integrated with data augmentation and semi-supervised learning, but barely perform better than the random baseline. In this work, we evaluate them under more realistic settings and propose a more suitable evaluation protocol. For semantic segmentation, previous academic studies focused on diverse datasets with substantial annotation resources. In contrast, data collected in many driving scenarios is highly redundant, and most medical applications are subject to very constrained annotation budgets. The study evaluates active learning techniques under various conditions including data redundancy, the use of semi-supervised learning, and differing annotation budgets. As an outcome of our study, we provide a comprehensive usage guide to obtain the best performance for each case.
AbstractList	Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Recently, deep active learning has shown success on various tasks. However, the conventional evaluation schemes are either incomplete or below par. This study critically assesses various active learning approaches, identifying key factors essential for choosing the most effective active learning method. It includes a comprehensive guide to obtain the best performance for each case, in image classification and semantic segmentation. For image classification, the AL methods improve by a large-margin when integrated with data augmentation and semi-supervised learning, but barely perform better than the random baseline. In this work, we evaluate them under more realistic settings and propose a more suitable evaluation protocol. For semantic segmentation, previous academic studies focused on diverse datasets with substantial annotation resources. In contrast, data collected in many driving scenarios is highly redundant, and most medical applications are subject to very constrained annotation budgets. The study evaluates active learning techniques under various conditions including data redundancy, the use of semi-supervised learning, and differing annotation budgets. As an outcome of our study, we provide a comprehensive usage guide to obtain the best performance for each case.
Author	Brox, Thomas Çiçek, Özgün Ehrhardt, Jan Handels, Heinz Mittal, Sudhanshu Tatarchenko, Maxim Niemeijer, Joshua Schäfer, Jörg P.
Author_xml	– sequence: 1 givenname: Sudhanshu orcidid: 0000-0002-7809-8058 surname: Mittal fullname: Mittal, Sudhanshu email: mittal@cs.uni-freiburg.de organization: University of Freiburg – sequence: 2 givenname: Joshua surname: Niemeijer fullname: Niemeijer, Joshua email: Joshua.Niemeijer@dlr.de organization: German Aerospace Center (DLR), University of Luebeck – sequence: 3 givenname: Özgün surname: Çiçek fullname: Çiçek, Özgün organization: Robert Bosch GmbH – sequence: 4 givenname: Maxim surname: Tatarchenko fullname: Tatarchenko, Maxim organization: Robert Bosch GmbH – sequence: 5 givenname: Jan surname: Ehrhardt fullname: Ehrhardt, Jan organization: University of Luebeck – sequence: 6 givenname: Jörg P. surname: Schäfer fullname: Schäfer, Jörg P. organization: German Aerospace Center (DLR) – sequence: 7 givenname: Heinz surname: Handels fullname: Handels, Heinz organization: University of Luebeck – sequence: 8 givenname: Thomas surname: Brox fullname: Brox, Thomas organization: University of Freiburg
BookMark	eNp9kE1LAzEQhoNUsK3-AU8Bz6uZZHeTPZZaP6AgWD2HbDq7pGyzNdkW7K932xW8eRjmMO_zDjwTMvKtR0Jugd0DY_IhAvBcJIxn_QjJk-MFGUMmRQIpy0ZkzArOkiwv4IpMYtwwxrjiYkz0O5rGxc5ZujiYZm8613raVvQRcUdntnMHpEs0wTtf06oN9HVraqTzxsToKmcHwPg1XeHW-FPRCust-u58uSaXlWki3vzuKfl8WnzMX5Ll2_PrfLZMrIC0SwyTygAIwDwtOZcCVK6UQFsiY6XNVZEWkqUmFUIUVZlLsNLYNa9EmSlTVmJK7obeXWi_9hg7vWn3wfcvteCQZwoKJfsUH1I2tDEGrPQuuK0J3xqYPonUg0jdi9RnkfrYQ2KAYh_2NYa_6n-oH3ZMeC0
Cites_doi	10.1007/s11263-009-0275-4 10.1007/978-3-030-58586-0_40 10.1109/CVPR.2019.00018 10.1109/CVPR46437.2021.01084 10.1109/TPAMI.2019.2960224 10.1145/3472291 10.1109/TNNLS.2024.3396463 10.1007/978-3-030-01234-2_49 10.1109/ISBI.2018.8363547 10.1109/CVPR.2009.5206848 10.1109/ICCVW54120.2021.00194 10.1109/ICCV.2011.6126343 10.1109/CVPR.2016.350 10.1109/TCSVT.2016.2589879 10.1002/j.1538-7305.1948.tb01338.x 10.1007/978-3-030-58607-2_30 10.1016/j.patrec.2008.04.005 10.1109/ICCV.2019.00607 10.1109/MSP.2012.2211477 10.1093/bioinformatics/btz083 10.7551/mitpress/9780262033589.001.0001 10.1109/BIBM.2016.7822557 10.2307/2575887 10.1109/CVPR52688.2022.00421 10.1109/ICRA.2014.6907021 10.48550/ARXIV.2210.08403 10.1109/CVPR.2019.00020 10.1109/CVPR52688.2022.00032 10.1609/aaai.v35i9.16988 10.5244/C.30.87 10.1145/130385.130417 10.1109/CVPR.2018.00976 10.1016/j.patcog.2019.01.006 10.1109/TPAMI.2017.2699184 10.1109/CVPR46437.2021.00807 10.1007/978-3-319-66179-7_46
ContentType	Journal Article
Copyright	The Author(s) 2025 Copyright Springer Nature B.V. Jul 2025
Copyright_xml	– notice: The Author(s) 2025 – notice: Copyright Springer Nature B.V. Jul 2025
DBID	C6C AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D
DOI	10.1007/s11263-025-02372-z
DatabaseName	Springer Nature OA Free Journals CrossRef Computer and Information Systems 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 Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional
DatabaseTitleList	CrossRef Computer and Information Systems Abstracts
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences Computer Science
EISSN	1573-1405
EndPage	4316
ExternalDocumentID	10_1007_s11263_025_02372_z
GrantInformation_xml	– fundername: Deutsche Forschungsgemeinschaft funderid: http://dx.doi.org/10.13039/501100001659 – fundername: Bundesministerium für Wirtschaft und Klimaschutz funderid: http://dx.doi.org/10.13039/100021130
GroupedDBID	-Y2 -~C .4S .86 .DC .VR 06D 0R~ 0VY 199 1N0 1SB 2.D 203 28- 29J 2J2 2JN 2JY 2KG 2KM 2LR 2P1 2VQ 2~H 30V 4.4 406 408 409 40D 40E 5GY 5QI 5VS 67Z 6NX 6TJ 78A 7WY 8FE 8FG 8FL 8TC 8UJ 95- 95. 95~ 96X AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AAOBN AAPKM AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBRH ABBXA ABDBE ABDBF ABDZT ABECU ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABUWG ABWNU ABXPI ACAOD ACBXY ACDTI ACGFO ACGFS ACHSB ACHXU ACIHN ACKNC ACMDZ ACMFV ACMLO ACOKC ACOMO ACPIV ACREN ACUHS ACZOJ ADHHG ADHIR ADHKG ADIMF ADKFA ADKNI ADKPE ADMLS ADRFC ADTPH ADURQ ADYFF ADYOE ADZKW AEAQA AEBTG AEFIE AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFDZB AFEXP AFGCZ AFKRA AFLOW AFOHR AFQWF AFWTZ AFYQB AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGQPQ AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHPBZ AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMTXH AMXSW AMYLF AMYQR AOCGG ARAPS ARCSS ARMRJ ASPBG ATHPR AVWKF AXYYD AYFIA AYJHY AZFZN AZQEC B-. B0M BA0 BBWZM BDATZ BENPR BEZIV BGLVJ BGNMA BPHCQ BSONS C6C CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 DWQXO EAD EAP EAS EBLON EBS EDO EIOEI EJD EMK EPL ESBYG ESX F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRNLG FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNUQQ GNWQR GQ7 GQ8 GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I-F I09 IAO ICD IHE IJ- IKXTQ ISR ITC ITM IWAJR IXC IZIGR IZQ I~X I~Y I~Z J-C J0Z JBSCW JCJTX JZLTJ K60 K6V K6~ K7- KDC KOV KOW LAK LLZTM M0C M4Y MA- N2Q N9A NB0 NDZJH NPVJJ NQJWS NU0 O9- O93 O9G O9I O9J OAM OVD P19 P2P P62 P9O PF0 PHGZM PHGZT PMFND PQBIZ PQBZA PQQKQ PROAC PT4 PT5 QF4 QM1 QN7 QO4 QOK QOS R4E R89 R9I RHV RNI RNS ROL RPX RSV RZC RZE RZK S16 S1Z S26 S27 S28 S3B SAP SCJ SCLPG SCO SDH SDM SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 T16 TAE TEORI TSG TSK TSV TUC TUS U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 ZMTXR ~8M ~EX AAYXX ABFSG ABRTQ ACSTC AEZWR AFFHD AFHIU AHWEU AIXLP CITATION PQGLB 7SC 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c314t-a078a1131e64b2273186883ecbe00bc68949704a43339fb671c7acd2f3b58abf3
IEDL.DBID	RSV
ISICitedReferencesCount	2
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001434110600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0920-5691
IngestDate	Wed Nov 05 08:00:02 EST 2025 Sat Nov 29 07:49:47 EST 2025 Sun Jun 08 01:10:19 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	7
Keywords	Segmentation Active learning Semi supervised learning Classification
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c314t-a078a1131e64b2273186883ecbe00bc68949704a43339fb671c7acd2f3b58abf3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-7809-8058
OpenAccessLink	https://link.springer.com/10.1007/s11263-025-02372-z
PQID	3216581987
PQPubID	1456341
PageCount	23
ParticipantIDs	proquest_journals_3216581987 crossref_primary_10_1007_s11263_025_02372_z springer_journals_10_1007_s11263_025_02372_z
PublicationCentury	2000
PublicationDate	20250700 2025-07-00 20250701
PublicationDateYYYYMMDD	2025-07-01
PublicationDate_xml	– month: 7 year: 2025 text: 20250700
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	International journal of computer vision
PublicationTitleAbbrev	Int J Comput Vis
PublicationYear	2025
Publisher	Springer US Springer Nature B.V
Publisher_xml	– name: Springer US – name: Springer Nature B.V
References	M Everingham (2372_CR16) 2010; 88 M Amgad (2372_CR1) 2019; 35 2372_CR17 2372_CR58 2372_CR13 2372_CR57 2372_CR15 2372_CR59 2372_CR10 2372_CR54 2372_CR53 2372_CR12 2372_CR56 O Chapelle (2372_CR7) 2006 2372_CR11 2372_CR55 2372_CR50 2372_CR52 2372_CR51 Y Gal (2372_CR18) 2016; 48 2372_CR29 2372_CR28 2372_CR25 2372_CR24 Y Gal (2372_CR19) 2017; 70 2372_CR27 2372_CR26 2372_CR21 2372_CR20 2372_CR23 2372_CR22 2372_CR61 2372_CR60 CE Shannon (2372_CR45) 1948; 27 2372_CR62 2372_CR39 2372_CR36 S Mittal (2372_CR34) 2019; 43 2372_CR35 C Blundell (2372_CR4) 2015; 37 2372_CR38 2372_CR37 2372_CR31 2372_CR33 D Li (2372_CR32) 2024 GJ Brostow (2372_CR5) 2008; 30 2372_CR30 2372_CR8 2372_CR6 2372_CR3 2372_CR2 L Chen (2372_CR9) 2018; 40 2372_CR47 2372_CR46 2372_CR49 P Ren (2372_CR42) 2021; 54 2372_CR48 2372_CR43 2372_CR44 2372_CR41 2372_CR40 L Deng (2372_CR14) 2012; 29
References_xml	– volume: 88 start-page: 303 year: 2010 ident: 2372_CR16 publication-title: International Journal of Computer Vision doi: 10.1007/s11263-009-0275-4 – ident: 2372_CR47 – ident: 2372_CR24 – ident: 2372_CR30 – ident: 2372_CR50 doi: 10.1007/978-3-030-58586-0_40 – ident: 2372_CR57 doi: 10.1109/CVPR.2019.00018 – ident: 2372_CR6 doi: 10.1109/CVPR46437.2021.01084 – ident: 2372_CR37 – volume: 43 start-page: 1369 issue: 4 year: 2019 ident: 2372_CR34 publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2019.2960224 – volume: 54 start-page: 1 issue: 9 year: 2021 ident: 2372_CR42 publication-title: ACM Computing Surveys (CSUR) doi: 10.1145/3472291 – volume: 37 start-page: 1613 year: 2015 ident: 2372_CR4 publication-title: International Conference on Machine Learning – year: 2024 ident: 2372_CR32 publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2024.3396463 – ident: 2372_CR8 doi: 10.1007/978-3-030-01234-2_49 – volume: 70 start-page: 1183 year: 2017 ident: 2372_CR19 publication-title: International Conference on Machine Learning – ident: 2372_CR10 doi: 10.1109/ISBI.2018.8363547 – ident: 2372_CR27 – ident: 2372_CR13 doi: 10.1109/CVPR.2009.5206848 – ident: 2372_CR46 doi: 10.1109/ICCVW54120.2021.00194 – ident: 2372_CR23 doi: 10.1109/ICCV.2011.6126343 – ident: 2372_CR15 – ident: 2372_CR58 – ident: 2372_CR11 doi: 10.1109/CVPR.2016.350 – ident: 2372_CR60 – ident: 2372_CR33 – ident: 2372_CR52 doi: 10.1109/TCSVT.2016.2589879 – volume: 27 start-page: 379 year: 1948 ident: 2372_CR45 publication-title: The Bell System Technical Journal doi: 10.1002/j.1538-7305.1948.tb01338.x – ident: 2372_CR20 doi: 10.1007/978-3-030-58607-2_30 – ident: 2372_CR43 – volume: 30 start-page: 88 year: 2008 ident: 2372_CR5 publication-title: Pattern Recognition Letters doi: 10.1016/j.patrec.2008.04.005 – volume: 48 start-page: 1050 year: 2016 ident: 2372_CR18 publication-title: International Conference on Machine Learning – ident: 2372_CR49 doi: 10.1109/ICCV.2019.00607 – ident: 2372_CR22 – volume: 29 start-page: 141 year: 2012 ident: 2372_CR14 publication-title: IEEE Signal Processing Magazine doi: 10.1109/MSP.2012.2211477 – volume: 35 start-page: 3461 issue: 18 year: 2019 ident: 2372_CR1 publication-title: Bioinformatics doi: 10.1093/bioinformatics/btz083 – volume-title: Semi-supervised learning year: 2006 ident: 2372_CR7 doi: 10.7551/mitpress/9780262033589.001.0001 – ident: 2372_CR61 doi: 10.1109/BIBM.2016.7822557 – ident: 2372_CR2 – ident: 2372_CR26 doi: 10.2307/2575887 – ident: 2372_CR51 doi: 10.1109/CVPR52688.2022.00421 – ident: 2372_CR55 – ident: 2372_CR39 doi: 10.1109/ICRA.2014.6907021 – ident: 2372_CR36 – ident: 2372_CR40 doi: 10.48550/ARXIV.2210.08403 – ident: 2372_CR12 doi: 10.1109/CVPR.2019.00020 – ident: 2372_CR35 doi: 10.1109/CVPR52688.2022.00032 – ident: 2372_CR48 – ident: 2372_CR28 doi: 10.1609/aaai.v35i9.16988 – ident: 2372_CR25 – ident: 2372_CR59 doi: 10.5244/C.30.87 – ident: 2372_CR21 – ident: 2372_CR44 doi: 10.1145/130385.130417 – ident: 2372_CR17 – ident: 2372_CR38 – ident: 2372_CR53 doi: 10.1109/TCSVT.2016.2589879 – ident: 2372_CR3 doi: 10.1109/CVPR.2018.00976 – ident: 2372_CR54 doi: 10.1016/j.patcog.2019.01.006 – ident: 2372_CR31 – ident: 2372_CR41 – ident: 2372_CR62 – volume: 40 start-page: 834 year: 2018 ident: 2372_CR9 publication-title: IEEE transactions on pattern analysis and machine intelligence doi: 10.1109/TPAMI.2017.2699184 – ident: 2372_CR29 doi: 10.1109/CVPR46437.2021.00807 – ident: 2372_CR56 doi: 10.1007/978-3-319-66179-7_46
SSID	ssj0002823
Score	2.4858696
Snippet	Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most...
SourceID	proquest crossref springer
SourceType	Aggregation Database Index Database Publisher
StartPage	4294
SubjectTerms	Artificial Intelligence Budgets Computer Imaging Computer Science Data augmentation Datasets German Conference on Pattern Recognition special issues (GCPR) Image annotation Image classification Image Processing and Computer Vision Image segmentation Labeling Machine learning Pattern Recognition Pattern Recognition and Graphics Redundancy Semantic segmentation Semantics Semi-supervised learning Vision
Title	Realistic Evaluation of Deep Active Learning for Image Classification and Semantic Segmentation
URI	https://link.springer.com/article/10.1007/s11263-025-02372-z https://www.proquest.com/docview/3216581987
Volume	133
WOSCitedRecordID	wos001434110600001&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: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1573-1405 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002823 issn: 0920-5691 databaseCode: RSV dateStart: 19970101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwELagMLBQnqJQkAc2iBTbedhjBa1AQhVqoeoW2Y5TMTSt2sLQX8_FcRqBYIDViZ3IZ9999t19h9C14iL1dRh6ErCoF4DJ8IRWyqM85RkNU03sne7oKe73-Xgsnl1S2LKKdq9cklZT18luhFqfY5FRzGLqrbfRDpg7XmzHwXC00b9wiCgLyMPBKIwEcakyP4_x1RzVGPObW9Ram17zf_95gPYdusSdcjkcoi2TH6GmQ5rY7eMlNFXFHKq2Y5QMTMGFCB1xd8MAjmcZvjdmjjtWLWLHxjrBAHXx4xR0EbZVNYt4o7KDzOE7ZgrygoGGZjJ1uU35CXrtdV_uHjxXfcHTjAQrTwJ4kIQwYqJAUUA5BbE-Z0Yr4_tKR1wEIvYDGTDGRKaimOhY6pRmTIVcqoydokY-y80Zwr4WGlas4qlgoJilFBmhhqpIKBrHadZCN5UQknlJspHUdMrFdCYwnYmdzmTdQu1KTonbcMuEUQJYqrhBaaHbSi71499HO__b6xdoj1rRFgG7bdRYLd7NJdrVH6u35eLKLsRPm3HYvg
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwED5BQYKFN6JQwAMbRIrtvDxWPASiVKg8xGbZjlMxNK1oYeDXc3EdKhAMsDqxE92d7z77XgBHOhN5aOI4UIhFgwhNRiCM1gHL8qxgcW6ou9N97KTdbvb0JG59Uti4jnavXZJOU8-S3ShzPscqo5inLHifh4UILVYVyNe7e_zUv3iImDaQx4NRnAjqU2V-XuOrOZphzG9uUWdtLlb_959rsOLRJWlPxWEd5my5AaseaRK_j8c4VDdzqMc2QfZsVQsRJ5LzzwrgZFiQM2tHpO3UIvHVWPsEoS65GqAuIq6rZhVvNJ2gSvyOHSC_cKE72x_43KZyCx4uzu9PLwPffSEwnEaTQCF4UJRyapNIM0Q5VWH9jFujbRhqk2QiEmkYqYhzLgqdpNSkyuSs4DrOlC74NjTKYWl3gIRGGJRYneWCo2JWShSUWaYToVma5kUTjmsmyNG0yIaclVOuyCmRnNKRU743oVXzSfoNN5acUcRS1Q1KE05qvswe_77a7t9eP4Sly_ubjuxcda_3YJk5NlfBuy1oTF5e7T4smrfJ8_jlwAnlB81i26I
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwED7xEmKhPEV5emCDiNjOy2MFVCBQhXiJzbIdp2JoqGhh4NdzdhIKCAbE6sSXyGffffb5vgPY15nIQxPHgUIsGkToMgJhtA5YlmcFi3ND_Znu_WXa62UPD-LqUxa_v-3ehCSrnAbH0lSOj4Z5cTRJfKPMxx9ddjFPWfA2DbORKxrk9us39x-2GDcUVTF53CTFiaB12szPMr66pgne_BYi9Z6n2_r_Py_BYo06SaeaJsswZcsVaNUIlNTre4RNTZGHpm0V5LV1HInYkZx-MIOTp4KcWDskHW8uSc3S2icIgcn5AG0U8dU23T2kqoMq8Tt2gHpEQTe2P6hznso1uOue3h6fBXVVhsBwGo0DhaBCUcqpTSLNEP04wv2MW6NtGGqTZCISaRipiHMuCp2k1KTK5KzgOs6ULvg6zJRPpd0AEhphcCbrLBccDbZSoqDMMp0IzdI0L9pw0ChEDivyDTmhWXbDKXE4pR9O-daG7UZnsl6II8kZRYzlTlbacNjoaPL4d2mbf3t9D-avTrry8rx3sQULzGvZ3endhpnx84vdgTnzOn4cPe_6-fkOl4zkhg
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=Realistic+Evaluation+of+Deep+Active+Learning+for+Image+Classification+and+Semantic+Segmentation&rft.jtitle=International+journal+of+computer+vision&rft.au=Mittal%2C+Sudhanshu&rft.au=Niemeijer%2C+Joshua&rft.au=%C3%87i%C3%A7ek%2C+%C3%96zg%C3%BCn&rft.au=Tatarchenko%2C+Maxim&rft.date=2025-07-01&rft.issn=0920-5691&rft.eissn=1573-1405&rft.volume=133&rft.issue=7&rft.spage=4294&rft.epage=4316&rft_id=info:doi/10.1007%2Fs11263-025-02372-z&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s11263_025_02372_z
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0920-5691&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0920-5691&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0920-5691&client=summon