DC FieldValueLanguage
dc.contributor.authorKrstanović, Lidijaen_US
dc.contributor.authorPopović, Branislaven_US
dc.contributor.authorJanev, Markoen_US
dc.contributor.authorBrkljač, Brankoen_US
dc.date.accessioned2022-04-27T11:33:57Z-
dc.date.available2022-04-27T11:33:57Z-
dc.date.issued2022-04-01-
dc.identifier.issn2076-3417-
dc.description.abstractMost CycleGAN domain transfer architectures require a large amount of data belonging to domains on which the domain transfer task is to be applied. Nevertheless, in many real-world applications one of the domains is reduced, i.e., scarce. This means that it has much less training data available in comparison to the other domain, which is fully observable. In order to tackle the problem of using CycleGAN framework in such unfavorable application scenarios, we propose and invoke a novel Bootstrapped SSL CycleGAN architecture (BTS-SSL), where the mentioned problem is overcome using two strategies. Firstly, by using a relatively small percentage of available labelled training data from the reduced or scarce domain and a Semi-Supervised Learning (SSL) approach, we prevent overfitting of the discriminator belonging to the reduced domain, which would otherwise occur during initial training iterations due to the small amount of available training data in the scarce domain. Secondly, after initial learning guided by the described SSL strategy, additional bootstrapping (BTS) of the reduced data domain is performed by inserting artifically generated training examples into the training poll of the data discriminator belonging to the scarce domain. Bootstrapped samples are generated by the already trained neural network that performs transferring from the fully observable to the scarce domain. The described procedure is periodically repeated during the training process several times and results in significantly improved performance of the final model in comparison to the original unsupervised CycleGAN approach. The same also holds in comparison to the solutions that are exclusively based either on the described SSL, or on the bootstrapping strategy, i.e., when these are applied separately. Moreover, in the considered scarce scenarios it also shows competitive results in comparison to the fully supervised solution based on the pix2pix method. In that sense, it is directly applicable to many domain transfer tasks that are relying on the CycleGAN architecture.en_US
dc.publisherMDPIen_US
dc.relation.ispartofApplied Sciences (Switzerland)en_US
dc.subjectbootstrapping | CycleGAN architecture | imbalanced data | semi-supervised learningen_US
dc.titleBootstrapped SSL CycleGAN for Asymmetric Domain Transferen_US
dc.typeArticleen_US
dc.identifier.doi10.3390/app12073411-
dc.identifier.scopus2-s2.0-85127808973-
dc.contributor.affiliationMechanicsen_US
dc.contributor.affiliationMathematical Institute of the Serbian Academy of Sciences and Artsen_US
dc.relation.firstpage3411-
dc.relation.issue7-
dc.relation.volume12-
dc.description.rank~M22-
item.grantfulltextnone-
item.cerifentitytypePublications-
item.fulltextNo Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.openairetypeArticle-
Show simple item record

Page view(s)

11
checked on Oct 3, 2022

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.