000891562 001__ 891562
000891562 005__ 20230228121558.0
000891562 0247_ $$2doi$$a10.3390/cryst11030258
000891562 0247_ $$2Handle$$a2128/33772
000891562 0247_ $$2WOS$$aWOS:000633604100001
000891562 037__ $$aFZJ-2021-01587
000891562 082__ $$a540
000891562 1001_ $$0P:(DE-HGF)0$$aTrampert, Patrick$$b0
000891562 245__ $$aDeep Neural Networks for Analysis of Microscopy Images—Synthetic Data Generation and Adaptive Sampling
000891562 260__ $$aBasel$$bMDPI$$c2021
000891562 3367_ $$2DRIVER$$aarticle
000891562 3367_ $$2DataCite$$aOutput Types/Journal article
000891562 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1674638221_19560
000891562 3367_ $$2BibTeX$$aARTICLE
000891562 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000891562 3367_ $$00$$2EndNote$$aJournal Article
000891562 520__ $$aThe analysis of microscopy images has always been an important yet time consuming process in materials science. Convolutional Neural Networks (CNNs) have been very successfully used for a number of tasks, such as image segmentation. However, training a CNN requires a large amount of hand annotated data, which can be a problem for material science data. We present a procedure to generate synthetic data based on ad hoc parametric data modelling for enhancing generalization of trained neural network models. Especially for situations where it is not possible to gather a lot of data, such an approach is beneficial and may enable to train a neural network reasonably. Furthermore, we show that targeted data generation by adaptively sampling the parameter space of the generative models gives superior results compared to generating random data points.
000891562 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000891562 536__ $$0G:(EU-Grant)759419$$aMuDiLingo - A Multiscale Dislocation Language for Data-Driven Materials Science (759419)$$c759419$$fERC-2017-STG$$x1
000891562 588__ $$aDataset connected to CrossRef
000891562 7001_ $$0P:(DE-HGF)0$$aRubinstein, Dmitri$$b1
000891562 7001_ $$0P:(DE-HGF)0$$aBoughorbel, Faysal$$b2
000891562 7001_ $$0P:(DE-HGF)0$$aSchlinkmann, Christian$$b3
000891562 7001_ $$0P:(DE-HGF)0$$aLuschkova, Maria$$b4
000891562 7001_ $$00000-0002-2189-2429$$aSlusallek, Philipp$$b5
000891562 7001_ $$0P:(DE-HGF)0$$aDahmen, Tim$$b6
000891562 7001_ $$0P:(DE-Juel1)186075$$aSandfeld, Stefan$$b7$$eCorresponding author
000891562 773__ $$0PERI:(DE-600)2661516-2$$a10.3390/cryst11030258$$gVol. 11, no. 3, p. 258 -$$n3$$p258 -$$tCrystals$$v11$$x2073-4352$$y2021
000891562 8564_ $$uhttps://juser.fz-juelich.de/record/891562/files/Invoice_MDPI_crystals-1104158.pdf
000891562 8564_ $$uhttps://juser.fz-juelich.de/record/891562/files/crystals-11-00258.pdf$$yOpenAccess
000891562 8767_ $$8crystals-1104158$$92021-02-27$$d2021-04-06$$eAPC$$jZahlung erfolgt$$zBelegnr. 1200165361 / 2021
000891562 909CO $$ooai:juser.fz-juelich.de:891562$$pdnbdelivery$$popenCost$$pec_fundedresources$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
000891562 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)186075$$aForschungszentrum Jülich$$b7$$kFZJ
000891562 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
000891562 9141_ $$y2022
000891562 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2021-02-03
000891562 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000891562 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bCRYSTALS : 2019$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000891562 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Blind peer review$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2021-02-03
000891562 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2021-02-03
000891562 920__ $$lyes
000891562 9201_ $$0I:(DE-Juel1)IAS-9-20201008$$kIAS-9$$lMaterials Data Science and Informatics$$x0
000891562 980__ $$ajournal
000891562 980__ $$aVDB
000891562 980__ $$aUNRESTRICTED
000891562 980__ $$aI:(DE-Juel1)IAS-9-20201008
000891562 980__ $$aAPC
000891562 9801_ $$aAPC
000891562 9801_ $$aFullTexts