SelectingDataAugmentationforSimulatingInterventionsMaximilianIlse1JakubM.Tomczak2PatrickForre´1AbstractInthefieldofdomaingeneralization,onetriestofindarep-resentationthatgeneralizesacrossdifferent...
WhenDoesDataAugmentationHelpWithMembershipInferenceAttacks?YigitcanKaya1TudorDumitras,1Abstractetal.,2018;Shokrietal.,2017).Inparticular,thisenablesmembershipinferenceattacks(MIAs)tofindoutwhetherD...
JoiningdatasetsviadataAugmentationinthelabelspaceforneuralnetworksJakeZhao(Junbo)1MingfengOu23LinjiXue2YunkaiCui2SaiWu1GangChen1AbstractInstead,itsversatilitycanbesubstantiallyenhancedbyanovelframe...
ImprovingGeneralizationinMeta-learningviaTaskAugmentationHuaxiuYao†1Long-KaiHuang2LinjunZhang3YingWei4LiTian2JamesZou1JunzhouHuang2ZhenhuiLi5Abstractquicklylearninganewtaskwithaslittleasafewexampl...
DatasetCondensationwithDifferentiableSiameseAugmentationBoZhao1HakanBilen1Abstractmassivedatasets(e.g.(Kuznetsovaetal.,2020;Chenetal.,2020a;Kwiatkowskietal.,2019)).Forexample,ittakesInmanymachinele...
DataAugmentationforMeta-LearningRenkunNi1MicahGoldblum1AmrSharaf2KezhiKong1TomGoldstein1AbstractMeta-learningframeworksusedataformultiplepurposesduringeachgradientupdate,whichcreatesthepossibilityf...
DataAugmentationfordeeplearningbasedacceleratedMRIreconstructionwithlimiteddataZalanFabian1ReinhardHeckel2MahdiSoltanolkotabi1Abstracttients.Duetothesubsampling,therearefewerequationsthanunknowns,a...
Self-supervisedLabelAugmentationviaInputTransformationsHankookLee1SungJuHwang234JinwooShin21Abstractsentationlearningforimages(Doerschetal.,2015;Noroozi&Favaro,2016;Larssonetal.,2017;Gidarisetal.,2...
DistributionAugmentationforGenerativeModelingHeewooJun1RewonChild1MarkChen1JohnSchulman1AdityaRamesh1AlecRadford1IlyaSutskever1AbstractFigure1.Unconditionalsamplesfromalargeautoregressivemodeltrain...
PopulationBasedAugmentation:EfficientLearningofAugmentationPolicySchedulesDanielHo12EricLiang1IonStoica1PieterAbbeel13XiChen13AbstractBaselineAutoAugmentPopulationBasedAugmentation4Akeychallengeinl...
DoesDataAugmentationLeadtoPositiveMargin?ShashankRajput1ZhiliFeng1ZacharyCharles2Po-LingLoh3DimitrisPapailiopoulos2AbstractaugmentedImageNetusingtranslations,horizontalreflec-tions,andalteredintens...
AKernelTheoryofModernDataAugmentationTriDao1AlbertGu1AlexanderJ.Ratner1VirginiaSmith2ChristopherDeSa3ChristopherRe´1Abstractasregularizertomaketheresultingmodelmorerobust,andprovideresourcestodata...
Pseudo-taskAugmentation:FromDeepMultitaskLearningtoIntrataskSharing—andBackElliotMeyerson12RistoMiikkulainen12Abstract2018).DeepMTLreliesontrainingsignalsfrommultipledatasetstotraindeepstructureth...