FADE: A Task-Agnostic Upsampling Operator for Encoder–Decoder Architectures

The goal of this work is to develop a task-agnostic feature upsampling operator for dense prediction where the operator is required to facilitate not only region-sensitive tasks like semantic segmentation but also detail-sensitive tasks such as image matting. Prior upsampling operators often can wor...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	International journal of computer vision Ročník 133; číslo 1; s. 151 - 172
Hlavní autoři:	Lu, Hao, Liu, Wenze, Fu, Hongtao, Cao, Zhiguo
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York Springer US 01.01.2025 Springer Nature B.V
Témata:	Artificial Intelligence Computer Imaging Computer Science Encoders-Decoders Image Processing and Computer Vision Image segmentation Parameter sensitivity Pattern Recognition Pattern Recognition and Graphics Semantic segmentation Semantics Vision Instance segmentation Feature upsampling Semantic segmentation Object detection Image matting Dense prediction Depth estimation
ISSN:	0920-5691, 1573-1405
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	The goal of this work is to develop a task-agnostic feature upsampling operator for dense prediction where the operator is required to facilitate not only region-sensitive tasks like semantic segmentation but also detail-sensitive tasks such as image matting. Prior upsampling operators often can work well in either type of the tasks, but not both. We argue that task-agnostic upsampling should dynamically trade off between semantic preservation and detail delineation, instead of having a bias between the two properties. In this paper, we present FADE, a novel, plug-and-play, lightweight, and task-agnostic upsampling operator by fusing the assets of decoder and encoder features at three levels: (i) considering both the encoder and decoder feature in upsampling kernel generation; (ii) controlling the per-point contribution of the encoder/decoder feature in upsampling kernels with an efficient semi-shift convolutional operator; and (iii) enabling the selective pass of encoder features with a decoder-dependent gating mechanism for compensating details. To improve the practicality of FADE, we additionally study parameter- and memory-efficient implementations of semi-shift convolution. We analyze the upsampling behavior of FADE on toy data and show through large-scale experiments that FADE is task-agnostic with consistent performance improvement on a number of dense prediction tasks with little extra cost. For the first time, we demonstrate robust feature upsampling on both region- and detail-sensitive tasks successfully. Code is made available at: https://github.com/poppinace/fade
AbstractList	The goal of this work is to develop a task-agnostic feature upsampling operator for dense prediction where the operator is required to facilitate not only region-sensitive tasks like semantic segmentation but also detail-sensitive tasks such as image matting. Prior upsampling operators often can work well in either type of the tasks, but not both. We argue that task-agnostic upsampling should dynamically trade off between semantic preservation and detail delineation, instead of having a bias between the two properties. In this paper, we present FADE, a novel, plug-and-play, lightweight, and task-agnostic upsampling operator by fusing the assets of decoder and encoder features at three levels: (i) considering both the encoder and decoder feature in upsampling kernel generation; (ii) controlling the per-point contribution of the encoder/decoder feature in upsampling kernels with an efficient semi-shift convolutional operator; and (iii) enabling the selective pass of encoder features with a decoder-dependent gating mechanism for compensating details. To improve the practicality of FADE, we additionally study parameter- and memory-efficient implementations of semi-shift convolution. We analyze the upsampling behavior of FADE on toy data and show through large-scale experiments that FADE is task-agnostic with consistent performance improvement on a number of dense prediction tasks with little extra cost. For the first time, we demonstrate robust feature upsampling on both region- and detail-sensitive tasks successfully. Code is made available at: https://github.com/poppinace/fade The goal of this work is to develop a task-agnostic feature upsampling operator for dense prediction where the operator is required to facilitate not only region-sensitive tasks like semantic segmentation but also detail-sensitive tasks such as image matting. Prior upsampling operators often can work well in either type of the tasks, but not both. We argue that task-agnostic upsampling should dynamically trade off between semantic preservation and detail delineation, instead of having a bias between the two properties. In this paper, we present FADE, a novel, plug-and-play, lightweight, and task-agnostic upsampling operator by fusing the assets of decoder and encoder features at three levels: (i) considering both the encoder and decoder feature in upsampling kernel generation; (ii) controlling the per-point contribution of the encoder/decoder feature in upsampling kernels with an efficient semi-shift convolutional operator; and (iii) enabling the selective pass of encoder features with a decoder-dependent gating mechanism for compensating details. To improve the practicality of FADE, we additionally study parameter- and memory-efficient implementations of semi-shift convolution. We analyze the upsampling behavior of FADE on toy data and show through large-scale experiments that FADE is task-agnostic with consistent performance improvement on a number of dense prediction tasks with little extra cost. For the first time, we demonstrate robust feature upsampling on both region- and detail-sensitive tasks successfully. Code is made available at: https://github.com/poppinace/fade
Author	Liu, Wenze Fu, Hongtao Lu, Hao Cao, Zhiguo
Author_xml	– sequence: 1 givenname: Hao orcidid: 0000-0003-3854-8664 surname: Lu fullname: Lu, Hao organization: The Key Laboratory of Image Processing and Intelligent Control, Ministry of Education, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology – sequence: 2 givenname: Wenze orcidid: 0000-0002-1510-6196 surname: Liu fullname: Liu, Wenze organization: The Key Laboratory of Image Processing and Intelligent Control, Ministry of Education, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology – sequence: 3 givenname: Hongtao orcidid: 0000-0002-6692-0913 surname: Fu fullname: Fu, Hongtao organization: The Key Laboratory of Image Processing and Intelligent Control, Ministry of Education, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology – sequence: 4 givenname: Zhiguo orcidid: 0000-0002-9223-1863 surname: Cao fullname: Cao, Zhiguo email: zgcao@hust.edu.cn organization: The Key Laboratory of Image Processing and Intelligent Control, Ministry of Education, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology
BookMark	eNp9kL1OwzAUhS1UJNrCCzBFYjb42nHisEX9AaSiLu1sOa5dUlon2O7AxjvwhjwJoUVCYuhwdO9wvnuuzgD1XOMMQtdAboGQ_C4A0IxhQtNOUAAWZ6gPPGcYUsJ7qE8KSjDPCrhAgxA2hBAqKOuj52k5ntwnZbJQ4RWXa9eEWOtk2Qa1a7e1Wyfz1ngVG5_YThOnm5XxXx-fY3PYktLrlzoaHffehEt0btU2mKvfOUTL6WQxesSz-cPTqJxhzaCIuKLMpoVWjIPmdsWBaqEqC5ynilYsh0JVjGVArS1IakWaV4VSOs0yBZnIKRuim-Pd1jdvexOi3DR777pIyYBTxigI3rno0aV9E4I3Vra-3in_LoHIn9rksTbZ1SYPtUnRQeIfpOuoYt246FW9PY2yIxq6HLc2_u-rE9Q3FxKDDQ
CitedBy_id	crossref_primary_10_1016_j_asoc_2025_113643 crossref_primary_10_1371_journal_pone_0332931 crossref_primary_10_3390_rs17081438 crossref_primary_10_3390_agronomy14112734 crossref_primary_10_3390_s25165200 crossref_primary_10_3390_agriculture14122324
Cites_doi	10.1007/978-3-031-19812-0_14 10.1109/ICCV51070.2023.01140 10.1109/CVPR52688.2022.01179 10.1109/ICCV.2017.322 10.1109/CVPR.2018.00040 10.1007/978-3-030-58520-4_26 10.1109/CVPR.2017.41 10.1109/CVPR42600.2020.00982 10.1007/978-3-642-15549-9_1 10.1145/3355089.3356528 10.1109/CVPRW53098.2021.00286 10.1109/CVPR.2015.7298655 10.3115/v1/W14-4012 10.1109/CVPR46437.2021.01371 10.1109/CVPR.2016.90 10.1109/CVPR.2017.106 10.1109/CVPR.2018.00813 10.1109/TPAMI.2020.2983686 10.1109/TGRS.2022.3228927 10.1109/CVPR46437.2021.01508 10.1109/CVPR.2014.81 10.1007/s11263-009-0275-4 10.1109/CVPR.2015.7298965 10.1007/978-3-319-24574-4_28 10.1109/ICCV51070.2023.00371 10.1109/CVPR.2017.549 10.1109/CVPR.2019.00324 10.1007/978-3-030-58536-5_24 10.1109/CVPR.2016.207 10.1109/ICCV.2015.164 10.1109/ICCV.2019.00336 10.1109/CVPR52688.2022.01580 10.1007/978-3-642-33715-4_54 10.1109/ICCV.2019.00310 10.1109/TPAMI.2015.2439281 10.1109/CVPR.2017.660 10.1007/978-3-030-01234-2_49 10.1007/3-540-47967-8_8 10.1109/ICCV.2019.00533 10.1109/CVPR46437.2021.00677 10.1109/CVPR.2017.544 10.1109/CVPR52688.2022.01042 10.1109/ICCV.1998.710815 10.1109/TPAMI.2016.2644615 10.1109/ICCV48922.2021.00951 10.1609/aaai.v34i07.6805 10.1109/CVPR.2016.319 10.1007/978-3-319-10602-1_48 10.1007/978-3-319-10590-1_53 10.1007/s11263-021-01465-9 10.1109/CVPR.2009.5206503 10.1007/978-3-030-58452-8_45 10.1109/CVPR.2018.00913 10.1109/ICCV48922.2021.00090 10.1109/CVPR.2018.00591 10.1007/978-3-030-01228-1_26 10.1109/TPAMI.2020.3004474 10.1109/CVPR46437.2021.00681 10.1007/978-3-030-58568-6_39
ContentType	Journal Article
Copyright	The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Copyright Springer Nature B.V. Jan 2025
Copyright_xml	– notice: The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. – notice: Copyright Springer Nature B.V. Jan 2025
DBID	AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D
DOI	10.1007/s11263-024-02191-8
DatabaseName	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	Computer and Information Systems Abstracts
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences Computer Science
EISSN	1573-1405
EndPage	172
ExternalDocumentID	10_1007_s11263_024_02191_8
GrantInformation_xml	– fundername: National Natural Science Fundation of China grantid: 62106080
GroupedDBID	-4Z -59 -5G -BR -EM -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 3V. 4.4 406 408 409 40D 40E 5GY 5QI 5VS 67Z 6NX 6TJ 78A 7WY 8FE 8FG 8FL 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AAOBN AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA 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 ACMLO ACOKC ACOMO ACPIV ACREN ACUHS ACZOJ ADHHG ADHIR ADIMF ADINQ 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 AFEXP AFGCZ AFKRA AFLOW AFQWF AFWTZ AFYQB AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMTXH AMXSW AMYLF AMYQR AOCGG ARAPS ARCSS ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN AZQEC B-. B0M BA0 BBWZM BDATZ BENPR BEZIV BGLVJ BGNMA BPHCQ BSONS 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 GQ6 GQ7 GQ8 GROUPED_ABI_INFORM_COMPLETE GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I-F I09 IAO 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 M0N M4Y MA- N2Q N9A NB0 NDZJH NPVJJ NQJWS NU0 O9- O93 O9G O9I O9J OAM OVD P19 P2P P62 P9O PF0 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 Z7R Z7S Z7V Z7W Z7X Z7Y Z7Z Z83 Z86 Z88 Z8M Z8N Z8P Z8Q Z8R Z8S Z8T Z8W Z92 ZMTXR ~8M ~EX AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC ADHKG ADKFA AEZWR AFDZB AFFHD AFHIU AFOHR AGQPQ AHPBZ AHWEU AIXLP ATHPR AYFIA CITATION ICD PHGZM PHGZT PQGLB 7SC 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c319t-b23f49ca351c5fd512c8abf1554a2b3719ab33612ff904f847b9aac466a168723
IEDL.DBID	RSV
ISICitedReferencesCount	6
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001273975600001&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 08:26:28 EST 2025 Sat Nov 29 06:42:31 EST 2025 Tue Nov 18 20:42:56 EST 2025 Fri Feb 21 02:35:05 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	1
Keywords	Instance segmentation Feature upsampling Semantic segmentation Object detection Image matting Dense prediction Depth estimation
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c319t-b23f49ca351c5fd512c8abf1554a2b3719ab33612ff904f847b9aac466a168723
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-9223-1863 0000-0002-6692-0913 0000-0003-3854-8664 0000-0002-1510-6196
PQID	3152332185
PQPubID	1456341
PageCount	22
ParticipantIDs	proquest_journals_3152332185 crossref_primary_10_1007_s11263_024_02191_8 crossref_citationtrail_10_1007_s11263_024_02191_8 springer_journals_10_1007_s11263_024_02191_8
PublicationCentury	2000
PublicationDate	20250100 2025-01-00 20250101
PublicationDateYYYYMMDD	2025-01-01
PublicationDate_xml	– month: 1 year: 2025 text: 20250100
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	2191_CR72 2191_CR70 2191_CR71 2191_CR32 2191_CR30 2191_CR31 2191_CR36 Y Yuan (2191_CR66) 2021; 129 2191_CR37 2191_CR34 2191_CR35 S Niklaus (2191_CR38) 2019; 38 2191_CR61 2191_CR62 2191_CR60 2191_CR21 2191_CR65 2191_CR22 2191_CR63 2191_CR20 A Odena (2191_CR39) 2016; 1 2191_CR64 2191_CR69 2191_CR26 H Lu (2191_CR33) 2022; 44 2191_CR23 2191_CR67 2191_CR68 2191_CR29 2191_CR9 2191_CR8 2191_CR27 2191_CR7 2191_CR28 J Wu (2191_CR59) 2022; 60 J Wang (2191_CR57) 2021; 44 2191_CR51 V Badrinarayanan (2191_CR1) 2017; 39 2191_CR54 2191_CR11 2191_CR55 2191_CR52 2191_CR53 2191_CR14 2191_CR58 2191_CR15 2191_CR13 2191_CR18 2191_CR19 2191_CR16 2191_CR17 2191_CR6 2191_CR5 2191_CR4 2191_CR3 2191_CR2 C Dong (2191_CR10) 2015; 38 X Li (2191_CR24) 2020; 34 2191_CR40 X Li (2191_CR25) 2023; 132 2191_CR43 2191_CR44 2191_CR41 2191_CR42 2191_CR47 2191_CR48 2191_CR45 2191_CR46 M Tan (2191_CR50) 2019; 97 2191_CR49 M Everingham (2191_CR12) 2010; 88 J Wang (2191_CR56) 2020; 43
References_xml	– ident: 2191_CR34 doi: 10.1007/978-3-031-19812-0_14 – ident: 2191_CR41 – ident: 2191_CR30 doi: 10.1109/ICCV51070.2023.01140 – ident: 2191_CR68 doi: 10.1109/CVPR52688.2022.01179 – ident: 2191_CR16 doi: 10.1109/ICCV.2017.322 – ident: 2191_CR60 doi: 10.1109/CVPR.2018.00040 – ident: 2191_CR22 doi: 10.1007/978-3-030-58520-4_26 – ident: 2191_CR35 – ident: 2191_CR65 doi: 10.1109/CVPR.2017.41 – ident: 2191_CR19 doi: 10.1109/CVPR42600.2020.00982 – ident: 2191_CR14 doi: 10.1007/978-3-642-15549-9_1 – volume: 38 start-page: 1 issue: 6 year: 2019 ident: 2191_CR38 publication-title: ACM Trans Graph doi: 10.1145/3355089.3356528 – ident: 2191_CR18 doi: 10.1109/CVPRW53098.2021.00286 – ident: 2191_CR21 – ident: 2191_CR48 doi: 10.1109/CVPR.2015.7298655 – ident: 2191_CR8 doi: 10.3115/v1/W14-4012 – ident: 2191_CR51 doi: 10.1109/CVPR46437.2021.01371 – ident: 2191_CR61 – ident: 2191_CR15 doi: 10.1109/CVPR.2016.90 – ident: 2191_CR63 – ident: 2191_CR28 doi: 10.1109/CVPR.2017.106 – ident: 2191_CR58 doi: 10.1109/CVPR.2018.00813 – ident: 2191_CR42 – volume: 43 start-page: 3349 issue: 10 year: 2020 ident: 2191_CR56 publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2020.2983686 – volume: 60 start-page: 1 year: 2022 ident: 2191_CR59 publication-title: Transactions on Geoscience and Remote Sensing doi: 10.1109/TGRS.2022.3228927 – ident: 2191_CR6 doi: 10.1109/CVPR46437.2021.01508 – ident: 2191_CR13 doi: 10.1109/CVPR.2014.81 – volume: 44 start-page: 4674 issue: 9 year: 2021 ident: 2191_CR57 publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – volume: 88 start-page: 303 issue: 2 year: 2010 ident: 2191_CR12 publication-title: International Journal of Computer Vision doi: 10.1007/s11263-009-0275-4 – ident: 2191_CR31 doi: 10.1109/CVPR.2015.7298965 – ident: 2191_CR45 doi: 10.1007/978-3-319-24574-4_28 – ident: 2191_CR20 doi: 10.1109/ICCV51070.2023.00371 – ident: 2191_CR26 doi: 10.1109/CVPR.2017.549 – ident: 2191_CR53 doi: 10.1109/CVPR.2019.00324 – ident: 2191_CR52 doi: 10.1007/978-3-030-58536-5_24 – ident: 2191_CR46 doi: 10.1109/CVPR.2016.207 – ident: 2191_CR64 doi: 10.1109/ICCV.2015.164 – ident: 2191_CR32 doi: 10.1109/ICCV.2019.00336 – volume: 132 start-page: 1 issue: 2 year: 2023 ident: 2191_CR25 publication-title: International Journal of Computer Vision – ident: 2191_CR40 doi: 10.1109/CVPR52688.2022.01580 – ident: 2191_CR47 doi: 10.1007/978-3-642-33715-4_54 – ident: 2191_CR55 doi: 10.1109/ICCV.2019.00310 – volume: 38 start-page: 295 issue: 2 year: 2015 ident: 2191_CR10 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2015.2439281 – ident: 2191_CR37 – ident: 2191_CR69 doi: 10.1109/CVPR.2017.660 – ident: 2191_CR5 doi: 10.1007/978-3-030-01234-2_49 – ident: 2191_CR2 doi: 10.1007/3-540-47967-8_8 – ident: 2191_CR49 doi: 10.1109/ICCV.2019.00533 – ident: 2191_CR9 doi: 10.1109/CVPR46437.2021.00677 – ident: 2191_CR72 doi: 10.1109/CVPR.2017.544 – ident: 2191_CR44 doi: 10.1109/CVPR52688.2022.01042 – ident: 2191_CR54 doi: 10.1109/ICCV.1998.710815 – volume: 39 start-page: 2481 issue: 12 year: 2017 ident: 2191_CR1 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2016.2644615 – ident: 2191_CR4 doi: 10.1109/ICCV48922.2021.00951 – volume: 34 start-page: 11418 year: 2020 ident: 2191_CR24 publication-title: Proceedings of the AAAI Conference on Artificial Intelligence doi: 10.1609/aaai.v34i07.6805 – ident: 2191_CR71 doi: 10.1109/CVPR.2016.319 – ident: 2191_CR27 doi: 10.1007/978-3-319-10602-1_48 – ident: 2191_CR11 – ident: 2191_CR67 doi: 10.1007/978-3-319-10590-1_53 – volume: 129 start-page: 2375 issue: 8 year: 2021 ident: 2191_CR66 publication-title: International Journal of Computer Vision doi: 10.1007/s11263-021-01465-9 – ident: 2191_CR36 – ident: 2191_CR43 doi: 10.1109/CVPR.2009.5206503 – ident: 2191_CR23 doi: 10.1007/978-3-030-58452-8_45 – ident: 2191_CR29 doi: 10.1109/CVPR.2018.00913 – ident: 2191_CR17 doi: 10.1109/ICCV48922.2021.00090 – volume: 1 start-page: e3 issue: 10 year: 2016 ident: 2191_CR39 publication-title: Deconvolution and checkerboard artifacts. Distill – volume: 97 start-page: 6105 year: 2019 ident: 2191_CR50 publication-title: Proceedings of the International Conference on Machine Learning – ident: 2191_CR3 doi: 10.1109/CVPR.2018.00591 – ident: 2191_CR62 doi: 10.1007/978-3-030-01228-1_26 – volume: 44 start-page: 242 issue: 1 year: 2022 ident: 2191_CR33 publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2020.3004474 – ident: 2191_CR70 doi: 10.1109/CVPR46437.2021.00681 – ident: 2191_CR7 doi: 10.1007/978-3-030-58568-6_39
SSID	ssj0002823
Score	2.501517
Snippet	The goal of this work is to develop a task-agnostic feature upsampling operator for dense prediction where the operator is required to facilitate not only...
SourceID	proquest crossref springer
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	151
SubjectTerms	Artificial Intelligence Computer Imaging Computer Science Encoders-Decoders Image Processing and Computer Vision Image segmentation Parameter sensitivity Pattern Recognition Pattern Recognition and Graphics Semantic segmentation Semantics Vision
Title	FADE: A Task-Agnostic Upsampling Operator for Encoder–Decoder Architectures
URI	https://link.springer.com/article/10.1007/s11263-024-02191-8 https://www.proquest.com/docview/3152332185
Volume	133
WOSCitedRecordID	wos001273975600001&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 Journals 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/eLvHCXMwnV1PS8MwFA86PXhx_sXplBy8aaFt0jb1VnTDg07BbexWkjQRUepYp2e_g9_QT-JL1q4qKuihUNI0hJfkvd_L-4fQoaY-zWIROFLJyKGaAB80GWgDHoVcRRmX9h5yeBH1emw0iq_LoLCi8navTJKWU9fBbp5vbY4UHtAyHLaIlgKTbcbo6DfDOf8FJWJWQB4UoyCMvTJU5vsxPoujGmN-MYtaadNt_m-ea2i1RJc4mW2HdbSg8g3ULJEmLs9xAU1VMYeqbRNddmFNTnCC-7y4dxLjfweD4MG44MbpPL_FV2NlbfIYcC7u5CYYfvL28nqm7BtOPpgkii006Hb6p-dOWWvBkXAIp47wiaax5CTwZKAzgAGScaEN2uC-IJEXc0EIwCGtY5dqkGki5lzSMOReyCKfbKNG_pirHYSZ1iHXVGRGuXFdzl1XS84E01T5sQpayKtInsoyEbmph_GQ1imUDQlTIGFqSZiyFjqa_zOepeH4tXe7Wsm0PJJFSgCpEAKIBiZwXK1c_fnn0Xb_1n0PrfimRrC9pmmjxnTypPbRsnye3hWTA7tV3wFfy-Fj
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1bS8MwFA46BX1xXnE6NQ--aaFt0ptvRTcmblNwG76FNEtElDrW6bP_wX_oL_Eka1cVFfShUNI0hHNyku_k3BA6VNSlwyjxLCFFYFFFYB_UGWg9HvhcBkMuzD3koB10u-HNTXSVB4Vlhbd7YZI0O3UZ7Oa4xuZI4QEtwwrn0QLVZXa0jn49mO2_oERMC8iDYuT5kZOHynw_xufjqMSYX8yi5rRpVv83z1W0kqNLHE-Xwxqak-k6quZIE-dynEFTUcyhaNtAnSbw5ATHuMezeyvW_ncwCO6PMq6dztNbfDmSxiaPAefiRqqD4cdvL69n0rzh-INJIttE_Wajd9qy8loLlgAhnFiJSxSNBCeeIzw1BBggQp4ojTa4m5DAiXhCCMAhpSKbKjjTkohzQX2fO34YuGQLVdLHVG4jHCrlc0WToVZubJtz21aCh0moqHQj6dWQU5CciTwRua6H8cDKFMqahAxIyAwJWVhDR7N_RtM0HL_2rhecZLlIZowAUiEEEA1M4LjgXPn559F2_tb9AC21ep02a593L3bRsqvrBZsrmzqqTMZPcg8tiufJXTbeN8v2Hfj05Ec
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFA46RXxxXnE6NQ--abFt0ptvw20ozjl0G3sraZqIKHWs1Wf_g__QX-JJ1m5TVBAfCiVNQzgnJ_lOzg2hQ0ltGgeRY3DBPYNKAvugykDrMM9lwosZ1_eQ_ZbXbvuDQdCZieLX3u6FSXIc06CyNCXZyTCWJ9PAN8vW9kcKD2gchj-PFihoMsqp6-a2P9mLQaEYF5MHJclxAysPm_l-jM9H0xRvfjGR6pOnWf7_nFfRSo46cW28TNbQnEjWUTlHoDiX7xSaiiIPRdsGumoCr05xDXdZ-mDUlF8eDIJ7w5QpZ_TkDl8PhbbVY8C_uJGoIPnR--tbXeg3XJsxVaSbqNdsdM_OjbwGg8FBODMjsomkAWfEsbgjY4AH3GeRVCiE2RHxrIBFhABMkjIwqYSzLgoY49R1meX6nk22UCl5SsQ2wr6ULpM0ipXSY5qMmabkzI98SYUdCKeCrIL8Ic8TlKs6GY_hNLWyImEIJAw1CUO_go4m_wzH6Tl-7V0tuBrmopqGBBAMIYB0YALHBRenn38ebedv3Q_QUqfeDFsX7ctdtGyrMsL6JqeKStnoWeyhRf6S3aejfb2CPwD4tu0r
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=FADE%3A+A+Task-Agnostic+Upsampling+Operator+for+Encoder%E2%80%93Decoder+Architectures&rft.jtitle=International+journal+of+computer+vision&rft.date=2025-01-01&rft.pub=Springer+Nature+B.V&rft.issn=0920-5691&rft.eissn=1573-1405&rft.volume=133&rft.issue=1&rft.spage=151&rft.epage=172&rft_id=info:doi/10.1007%2Fs11263-024-02191-8&rft.externalDBID=HAS_PDF_LINK
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