DAugNet: Unsupervised, Multisource, Multitarget, and Life-Long Domain Adaptation for Semantic Segmentation of Satellite Images
The domain adaptation of satellite images has recently gained increasing attention to overcome the limited generalization abilities of machine learning models when segmenting large-scale satellite images. Most of the existing approaches seek for adapting the model from one domain to another. However...
Saved in:
Published in | IEEE transactions on geoscience and remote sensing Vol. 59; no. 2; pp. 1067 - 1081 |
---|---|
Main Authors | , , , , |
Format | Journal Article |
Language | English |
Published |
New York
IEEE
01.02.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The domain adaptation of satellite images has recently gained increasing attention to overcome the limited generalization abilities of machine learning models when segmenting large-scale satellite images. Most of the existing approaches seek for adapting the model from one domain to another. However, such single-source and single-target setting prevents the methods from being scalable solutions since, nowadays, multiple sources and target domains having different data distributions are usually available. Besides, the continuous proliferation of satellite images necessitates the classifiers to adapt to continuously increasing data. We propose a novel approach, coined DAugNet, for unsupervised, multisource, multitarget, and life-long domain adaptation of satellite images. It consists of a classifier and a data augmentor. The data augmentor, which is a shallow network, is able to perform style transfer between multiple satellite images in an unsupervised manner, even when new data are added over time. In each training iteration, it provides the classifier with diversified data, which makes the classifier robust to large data distribution difference between the domains. Our extensive experiments prove that DAugNet significantly better generalizes to new geographic locations than the existing approaches. |
---|---|
AbstractList | The domain adaptation of satellite images has recently gained increasing attention to overcome the limited generalization abilities of machine learning models when segmenting large-scale satellite images. Most of the existing approaches seek for adapting the model from one domain to another. However, such single-source and single-target setting prevents the methods from being scalable solutions since, nowadays, multiple sources and target domains having different data distributions are usually available. Besides, the continuous proliferation of satellite images necessitates the classifiers to adapt to continuously increasing data. We propose a novel approach, coined DAugNet, for unsupervised, multisource, multitarget, and life-long domain adaptation of satellite images. It consists of a classifier and a data augmentor. The data augmentor, which is a shallow network, is able to perform style transfer between multiple satellite images in an unsupervised manner, even when new data are added over time. In each training iteration, it provides the classifier with diversified data, which makes the classifier robust to large data distribution difference between the domains. Our extensive experiments prove that DAugNet significantly better generalizes to new geographic locations than the existing approaches. |
Author | Alliez, Pierre Tasar, Onur Giros, Alain Tarabalka, Yuliya Clerc, Sebastien |
Author_xml | – sequence: 1 givenname: Onur orcidid: 0000-0002-0191-6729 surname: Tasar fullname: Tasar, Onur email: onur.tasar@inria.fr organization: Alliez are with Computer Science Department, the Université Côte d'Azur and INRIA, Project-Team TITANE, Sophia Antipolis, France – sequence: 2 givenname: Alain surname: Giros fullname: Giros, Alain organization: Center National d'Études Spatiales, Toulouse, France – sequence: 3 givenname: Yuliya surname: Tarabalka fullname: Tarabalka, Yuliya organization: LuxCarta Technology, Mouans Sartoux, France – sequence: 4 givenname: Pierre surname: Alliez fullname: Alliez, Pierre organization: Alliez are with Computer Science Department, the Université Côte d'Azur and INRIA, Project-Team TITANE, Sophia Antipolis, France – sequence: 5 givenname: Sebastien orcidid: 0000-0002-7393-5910 surname: Clerc fullname: Clerc, Sebastien organization: ACRI-ST, Biot, France |
BookMark | eNo9kE1LAzEQhoNUsFV_gHgJeO3WfGyTXW-lfkJVsHpespvJEukmNckKXvztbmnxNDPM-87wPhM0ct4BQheUzCgl5fX7w9t6xggjM06IoIIeoTGdz4uMiDwfoTGhpchYUbITNInxkxCaz6kco9_bRd--QLrBHy72WwjfNoKe4ud-k2z0fWjgMCQVWkhTrJzGK2sgW3nX4lvfKevwQqttUsl6h40PeA2dcsk2Q9N24A4bb_BaJdhsbAL81KkW4hk6NmoT4fxQT9HH_d378jFbvT48LRerrOFcpExCzsqmVqopci0LJmstDDEANdOCcSFYXeeaAteS5GJIaXRRz4lsKBemNsBP0dX-7jb4rx5iqj6HbG54WbFclkUhhxuDiu5VTfAxBjDVNthOhZ-KkmqHudphrnaYqwPmwXO591gA-NeXlEtJJf8D5td8gQ |
CODEN | IGRSD2 |
CitedBy_id | crossref_primary_10_1109_TGRS_2022_3163278 crossref_primary_10_3390_rs16091626 crossref_primary_10_1109_JSTARS_2023_3340412 crossref_primary_10_3390_rs14030646 crossref_primary_10_3390_rs13245100 crossref_primary_10_3390_rs14235911 crossref_primary_10_1109_TGRS_2023_3344670 crossref_primary_10_1109_JSTARS_2022_3220875 crossref_primary_10_1109_TGRS_2023_3281420 crossref_primary_10_1109_ACCESS_2023_3318867 crossref_primary_10_1016_j_isprsjprs_2022_11_010 crossref_primary_10_1109_LGRS_2022_3213984 crossref_primary_10_1109_TGRS_2022_3203040 crossref_primary_10_1109_TGRS_2023_3345159 crossref_primary_10_3390_rs14194915 crossref_primary_10_1109_JSTARS_2021_3119001 crossref_primary_10_1109_JSTARS_2021_3134766 crossref_primary_10_3390_rs14071527 crossref_primary_10_1109_TGRS_2023_3281503 crossref_primary_10_1016_j_isprsjprs_2022_07_011 crossref_primary_10_3390_land13070928 crossref_primary_10_1109_TGRS_2021_3116672 crossref_primary_10_1016_j_measurement_2022_112352 crossref_primary_10_1109_TGRS_2022_3201688 crossref_primary_10_1109_TGRS_2022_3208618 crossref_primary_10_3390_app13031674 crossref_primary_10_3390_rs14010190 crossref_primary_10_1109_TIP_2022_3162471 crossref_primary_10_3390_rs14174380 crossref_primary_10_1109_TGRS_2021_3067513 crossref_primary_10_1109_TGRS_2024_3376719 crossref_primary_10_3390_rs13245035 crossref_primary_10_3390_rs15235498 crossref_primary_10_1109_JSTARS_2023_3335891 crossref_primary_10_1109_TGRS_2022_3179891 crossref_primary_10_1016_j_isprsjprs_2023_01_018 crossref_primary_10_1109_JSTARS_2022_3226705 crossref_primary_10_3390_rs16071293 crossref_primary_10_1109_TGRS_2021_3093004 crossref_primary_10_1109_TGRS_2022_3175387 crossref_primary_10_3390_rs15153909 crossref_primary_10_3390_info13050259 crossref_primary_10_1109_ACCESS_2021_3074640 crossref_primary_10_1109_TGRS_2021_3120001 crossref_primary_10_1109_JSTARS_2024_3385380 crossref_primary_10_1109_TAFFC_2022_3228695 crossref_primary_10_1016_j_compag_2023_107766 crossref_primary_10_1109_MGRS_2022_3145854 |
Cites_doi | 10.1109/CVPRW50498.2020.00104 10.1109/TGRS.2019.2953328 10.1109/TGRS.2002.803794 10.1016/S0167-8655(02)00053-3 10.1109/ICCV.2019.00149 10.1109/36.905255 10.1109/ICCV.2017.244 10.1109/TSMC.1973.4309314 10.1109/JSTARS.2019.2925416 10.1109/ICCV.2017.372 10.1109/TGRS.2013.2295819 10.1109/36.239898 10.1007/BF00056770 10.1109/IGARSS.2019.8900277 10.1109/TGRS.2012.2192740 10.1109/TIP.2019.2963389 10.1109/MGRS.2016.2548504 10.1109/ICASSP.2018.8462111 10.1109/TGRS.2018.2872850 10.13176/11.9 10.1109/CVPR.2018.00916 10.3390/info11020125 10.1109/TGRS.2020.2980417 10.1109/TPAMI.2009.57 10.1016/j.patcog.2017.10.007 10.1109/ICCV.2017.167 10.1109/TGRS.2007.912445 10.1109/IGARSS.2017.8127684 10.1016/0016-0032(80)90058-7 10.1109/TGRS.2012.2200045 10.1109/JSTARS.2012.2202881 10.1109/CVPR.2018.00780 10.1109/TGRS.2019.2926069 10.1109/CVPR.2018.00417 10.1109/TGRS.2019.2906689 10.1016/S0167-8655(00)00112-4 10.1109/CVPR.2016.90 10.3390/rs11111369 10.1109/TPAMI.2017.2699184 10.1109/ICRA.2018.8460982 10.1109/TGRS.2016.2612821 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021 |
DBID | 97E RIA RIE AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M |
DOI | 10.1109/TGRS.2020.3006161 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEL CrossRef Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace |
DatabaseTitle | CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management |
DatabaseTitleList | Aerospace Database |
Database_xml | – sequence: 1 dbid: RIE name: IEL url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering Physics |
EISSN | 1558-0644 |
EndPage | 1081 |
ExternalDocumentID | 10_1109_TGRS_2020_3006161 9137717 |
Genre | orig-research |
GrantInformation_xml | – fundername: ACRI-ST – fundername: Centre National d’Études Spatiales (CNES) |
GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AASAJ AAYOK ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AFRAH AI. AIBXA AKJIK ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RIG RNS RXW TAE TN5 VH1 XFK Y6R AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M |
ID | FETCH-LOGICAL-c336t-7e429cbaac84d7827bd6f0feeb2d623662bb4d1e3d7046892fd8b507c136fbfe3 |
IEDL.DBID | RIE |
ISSN | 0196-2892 |
IngestDate | Fri Sep 13 08:54:35 EDT 2024 Fri Aug 23 02:58:48 EDT 2024 Wed Jun 26 19:27:12 EDT 2024 |
IsDoiOpenAccess | false |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 2 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c336t-7e429cbaac84d7827bd6f0feeb2d623662bb4d1e3d7046892fd8b507c136fbfe3 |
ORCID | 0000-0002-0191-6729 0000-0002-7393-5910 |
OpenAccessLink | https://hal.science/hal-02893533/document |
PQID | 2479887662 |
PQPubID | 85465 |
PageCount | 15 |
ParticipantIDs | crossref_primary_10_1109_TGRS_2020_3006161 proquest_journals_2479887662 ieee_primary_9137717 |
PublicationCentury | 2000 |
PublicationDate | 2021-02-01 |
PublicationDateYYYYMMDD | 2021-02-01 |
PublicationDate_xml | – month: 02 year: 2021 text: 2021-02-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | New York |
PublicationPlace_xml | – name: New York |
PublicationTitle | IEEE transactions on geoscience and remote sensing |
PublicationTitleAbbrev | TGRS |
PublicationYear | 2021 |
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 ref59 ref15 ref58 ref53 ref52 ref55 ref54 zou (ref28) 2018 ref17 ref18 huang (ref25) 2018 ref46 ref45 ref47 ref44 hoffman (ref23) 2016 ref49 ref7 zhao (ref41) 2019 ref9 ref4 tasar (ref10) 2020 ref5 choi (ref14) 2019 gonzalez (ref16) 2006 kingma (ref61) 2014 ref40 ref35 ref34 ref37 ref36 ref31 hoffman (ref19) 2017 ref30 ref33 ref32 ref2 ref39 ref38 zhao (ref43) 2018 liu (ref22) 2017 kumar (ref51) 2020 zhang (ref50) 2019 yu (ref48) 2018 goodfellow (ref8) 2014 ref24 buslaev (ref6) 2020; 11 ref26 redko (ref42) 2018 ref20 ref21 lee (ref12) 2018 ronneberger (ref1) 2015 ref27 ref29 van etten (ref3) 2018 ref60 huang (ref11) 2018 |
References_xml | – ident: ref15 doi: 10.1109/CVPRW50498.2020.00104 – start-page: 700 year: 2017 ident: ref22 article-title: Unsupervised image-to-image translation networks publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: liu – year: 2018 ident: ref42 article-title: Optimal transport for multi-source domain adaptation under target shift publication-title: arXiv 1803 04899 contributor: fullname: redko – year: 2016 ident: ref23 article-title: FCNs in the wild: Pixel-level adversarial and constraint-based adaptation publication-title: arXiv 1612 02649 contributor: fullname: hoffman – ident: ref46 doi: 10.1109/TGRS.2019.2953328 – ident: ref31 doi: 10.1109/TGRS.2002.803794 – ident: ref30 doi: 10.1016/S0167-8655(02)00053-3 – start-page: 234 year: 2015 ident: ref1 article-title: U-net: Convolutional networks for biomedical image segmentation publication-title: Proc Int Conf Med Image Comput Comput -Assist Intervent -MICCAI contributor: fullname: ronneberger – ident: ref45 doi: 10.1109/ICCV.2019.00149 – ident: ref29 doi: 10.1109/36.905255 – ident: ref20 doi: 10.1109/ICCV.2017.244 – ident: ref57 doi: 10.1109/TSMC.1973.4309314 – ident: ref7 doi: 10.1109/JSTARS.2019.2925416 – year: 2019 ident: ref50 article-title: Online adaptation through meta-learning for stereo depth estimation publication-title: arXiv 1904 08462 contributor: fullname: zhang – start-page: 7285 year: 2019 ident: ref41 article-title: Multi-source domain adaptation for semantic segmentation publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: zhao – ident: ref58 doi: 10.1109/ICCV.2017.372 – ident: ref39 doi: 10.1109/TGRS.2013.2295819 – year: 2020 ident: ref10 article-title: SemI2I: Semantically consistent image-to-image translation for domain adaptation of remote sensing data publication-title: arXiv 2002 05925 contributor: fullname: tasar – ident: ref40 doi: 10.1109/36.239898 – ident: ref38 doi: 10.1007/BF00056770 – start-page: 289 year: 2018 ident: ref28 article-title: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training publication-title: Proc Eur Conf Comput Vis (ECCV) contributor: fullname: zou – ident: ref26 doi: 10.1109/IGARSS.2019.8900277 – year: 2014 ident: ref61 article-title: Adam: A method for stochastic optimization publication-title: arXiv 1412 6980 contributor: fullname: kingma – start-page: 8559 year: 2018 ident: ref43 article-title: Adversarial multiple source domain adaptation publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: zhao – ident: ref52 doi: 10.1109/TGRS.2012.2192740 – year: 2018 ident: ref3 article-title: SpaceNet: A remote sensing dataset and challenge series publication-title: arXiv 1807 01232 contributor: fullname: van etten – start-page: 35 year: 2018 ident: ref12 article-title: Diverse image-to-image translation via disentangled representations publication-title: Proc Eur Conf Comput Vis contributor: fullname: lee – ident: ref47 doi: 10.1109/TIP.2019.2963389 – ident: ref4 doi: 10.1109/MGRS.2016.2548504 – ident: ref27 doi: 10.1109/ICASSP.2018.8462111 – ident: ref33 doi: 10.1109/TGRS.2018.2872850 – year: 2020 ident: ref51 article-title: Understanding self-training for gradual domain adaptation publication-title: arXiv 2002 11361 contributor: fullname: kumar – ident: ref36 doi: 10.13176/11.9 – ident: ref13 doi: 10.1109/CVPR.2018.00916 – volume: 11 start-page: 125 year: 2020 ident: ref6 article-title: Albumentations: Fast and flexible image augmentations publication-title: Information doi: 10.3390/info11020125 contributor: fullname: buslaev – start-page: 2672 year: 2014 ident: ref8 article-title: Generative adversarial nets publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: goodfellow – ident: ref9 doi: 10.1109/TGRS.2020.2980417 – ident: ref32 doi: 10.1109/TPAMI.2009.57 – ident: ref54 doi: 10.1016/j.patcog.2017.10.007 – ident: ref56 doi: 10.1109/ICCV.2017.167 – ident: ref17 doi: 10.1109/TGRS.2007.912445 – ident: ref2 doi: 10.1109/IGARSS.2017.8127684 – year: 2019 ident: ref14 article-title: StarGAN v2: Diverse image synthesis for multiple domains publication-title: arXiv 1912 01865 contributor: fullname: choi – year: 2017 ident: ref19 article-title: CyCADA: Cycle-consistent adversarial domain adaptation publication-title: arXiv 1711 03213 contributor: fullname: hoffman – ident: ref37 doi: 10.1016/0016-0032(80)90058-7 – start-page: 590 year: 2018 ident: ref25 article-title: Domain transfer through deep activation matching publication-title: Proc Eur Conf Comput Vis (ECCV) contributor: fullname: huang – ident: ref18 doi: 10.1109/TGRS.2012.2200045 – ident: ref53 doi: 10.1109/JSTARS.2012.2202881 – ident: ref24 doi: 10.1109/CVPR.2018.00780 – ident: ref34 doi: 10.1109/TGRS.2019.2926069 – ident: ref44 doi: 10.1109/CVPR.2018.00417 – ident: ref55 doi: 10.1109/TGRS.2019.2906689 – start-page: 172 year: 2018 ident: ref11 article-title: Multimodal unsupervised image-to-image translation publication-title: Proc Eur Conf Comput Vis contributor: fullname: huang – ident: ref35 doi: 10.1016/S0167-8655(00)00112-4 – ident: ref59 doi: 10.1109/CVPR.2016.90 – ident: ref21 doi: 10.3390/rs11111369 – year: 2018 ident: ref48 article-title: Multi-target unsupervised domain adaptation without exactly shared categories publication-title: arXiv 1809 00852 contributor: fullname: yu – ident: ref60 doi: 10.1109/TPAMI.2017.2699184 – ident: ref49 doi: 10.1109/ICRA.2018.8460982 – ident: ref5 doi: 10.1109/TGRS.2016.2612821 – year: 2006 ident: ref16 publication-title: Digital Image Processing contributor: fullname: gonzalez |
SSID | ssj0014517 |
Score | 2.5871441 |
Snippet | The domain adaptation of satellite images has recently gained increasing attention to overcome the limited generalization abilities of machine learning models... |
SourceID | proquest crossref ieee |
SourceType | Aggregation Database Publisher |
StartPage | 1067 |
SubjectTerms | Adaptation Adaptation models Classifiers Convolutional neural networks (CNNs) Data dense labeling domain adaptation Domains generative adversarial networks (GANs) Geographical locations Image processing Image segmentation Iterative methods Learning algorithms life-long adaption Machine learning multisource adaption multitarget adaption Proliferation Remote sensing Satellite imagery Satellites Semantic segmentation Semantics Spaceborne remote sensing Standardization Training |
Title | DAugNet: Unsupervised, Multisource, Multitarget, and Life-Long Domain Adaptation for Semantic Segmentation of Satellite Images |
URI | https://ieeexplore.ieee.org/document/9137717 https://www.proquest.com/docview/2479887662/abstract/ |
Volume | 59 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV07b9swED4kAQq0Qx9Ji7pNCw6dCtOxKIqSshlJ07RIMtQxkE3g0zAKS0YlLR3y23OkaKOvoRsFSADBj7r7Pt6DAB-scFrlllNXuowipZa0kFzQLFe5VNKwRPpC4esbcbngX--yuz0Y72phrLUh-cxO_DDE8k2je39UdlL69nhJvg_7xZQNtVq7iAHPklgaLSiKCBYjmMm0PLn9_G2OSpChQPUeWyS_-aBwqcpflji4l4tncL2d2JBV8n3Sd2qif_7Rs_F_Z_4cnkaeSWbDxngBe7Y-hCe_dB88hEch-1O3R3B_PuuXN7Y7JYu67TfefLTWjEmozh2O9-PDkDg-JrI25GrlLL1q6iU5b9ZyVZOZkZshsk-QCpO5XSNsK42D5TqWONWkcWQuQxvQzpIvazRn7UtYXHy6Pbuk8WIGqtNUdBSxZaVWUuqCG6QYuTLCTZ1FlW6QTgnBlOImsanJUX4jGM4UComnTlLhlLPpKziom9q-BpJJKTKjlExdyWVhlM0UEwylsxQFL_MRfNxCVW2G_htV0C3TsvK4Vh7XKuI6giO_9LsX46qP4HgLbhX_0LZi3Hdqy3Gub_791Vt4zHz-SsjQPoaD7kdv3yEB6dT7sPMeANXC2gc |
link.rule.ids | 315,786,790,802,27957,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Nb9MwGH41hhDjMGBjWtkAHzihpmsSx0m4VYzRQdsDbaXdIn9WFWpSLcmFA7-d145b8XXg5kiOZPmx_T6P3w8DvNXMSJFqGpjcJAFSah5knLIgSUXKBVdRyG2i8HTGxkv6-S65O4D-PhdGa-2Cz_TANp0vX1WytVdlV7ktjxemD-Ah2vlh3mVr7X0GNAl9cjQLUEZE3oeJHa8Wn77OUQtGKFGtzWbhb1bIPavy11nsDMzNU5juhtbFlXwbtI0YyO9_VG3837E_g2PPNMmoWxrP4UCXJ_Dkl_qDJ_DIxX_K-hR-XI_a1Uw378myrNutPUBqrfrE5ed2F_z-owsd7xNeKjJZGx1MqnJFrqsNX5dkpPi28-0TJMNkrjcI3FpiY7XxSU4lqQyZc1cItNHkdoMHWv0CljcfFx_GgX-aIZBxzJoA0Y1yKTiXGVVIMlKhmBkajTpdIaFiLBKCqlDHKkUBjmAYlQmknjKMmRFGx2dwWFalPgeScM4SJQSPTU55poRORMQiFM-cZTRPe_BuB1Wx7SpwFE65DPPC4lpYXAuPaw9O7dTvO_pZ78HlDtzC79G6iKit1ZbiWF_--6838Hi8mE6Kye3sywUcRTaaxcVrX8Jhc9_qV0hHGvHarcKffnvdXQ |
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=DAugNet%3A+Unsupervised%2C+Multisource%2C+Multitarget%2C+and+Life-Long+Domain+Adaptation+for+Semantic+Segmentation+of+Satellite+Images&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Tasar%2C+Onur&rft.au=Giros%2C+Alain&rft.au=Tarabalka%2C+Yuliya&rft.au=Alliez%2C+Pierre&rft.date=2021-02-01&rft.pub=IEEE&rft.issn=0196-2892&rft.eissn=1558-0644&rft.volume=59&rft.issue=2&rft.spage=1067&rft.epage=1081&rft_id=info:doi/10.1109%2FTGRS.2020.3006161&rft.externalDocID=9137717 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon |