Show simple item record

dc.contributor.authorLemley, Joseph
dc.contributor.authorBazrafkan, Shabab
dc.contributor.authorCorcoran, Peter
dc.date.accessioned2018-10-08T14:15:38Z
dc.date.available2018-10-08T14:15:38Z
dc.date.issued2017-04-24
dc.identifier.citationLemley, J., Bazrafkan, S., & Corcoran, P. (2017). Smart Augmentation Learning an Optimal Data Augmentation Strategy. IEEE Access, 5, 5858-5869. doi: 10.1109/ACCESS.2017.2696121en_IE
dc.identifier.issn2169-3536
dc.identifier.urihttp://hdl.handle.net/10379/14586
dc.description.abstractA recurring problem faced when training neural networks is that there is typically not enough data to maximize the generalization capability of deep neural networks. There are many techniques to address this, including data augmentation, dropout, and transfer learning. In this paper, we introduce an additional method, which we call smart augmentation and we show how to use it to increase the accuracy and reduce over fitting on a target network. Smart augmentation works, by creating a network that learns how to generate augmented data during the training process of a target network in a way that reduces that networks loss. This allows us to learn augmentations that minimize the error of that network. Smart augmentation has shown the potential to increase accuracy by demonstrably significant measures on all data sets tested. In addition, it has shown potential to achieve similar or improved performance levels with significantly smaller network sizes in a number of tested cases.en_IE
dc.description.sponsorshipThis research is funded under the SFI Strategic Partnership Program by Science Foundation Ireland (SFI) and FotoNation Ltd. Project ID: 13/SPP/I2868 on Next Generation Imaging for Smartphone and Embedded Platforms. This work is also supported by an Irish Research Council Employment Based Programme Award. The authors gratefully acknowledge the support of NVIDIA Corporation with the donation of a Titan X GPU used for this research.en_IE
dc.formatapplication/pdfen_IE
dc.language.isoenen_IE
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_IE
dc.relation.ispartofIeee Accessen
dc.subjectArtificial intelligenceen_IE
dc.subjectArtificial neural networksen_IE
dc.subjectMachine learningen_IE
dc.subjectComputer vision supervised learningen_IE
dc.subjectMachine learning algorithmsen_IE
dc.subjectImage databasesen_IE
dc.titleSmart augmentation learning an optimal data augmentation strategyen_IE
dc.typeArticleen_IE
dc.date.updated2018-09-27T13:46:29Z
dc.identifier.doi10.1109/ACCESS.2017.2696121
dc.local.publishedsourcehttps://dx.doi.org/10.1109/ACCESS.2017.2696121en_IE
dc.description.peer-reviewedpeer-reviewed
dc.contributor.funderNVIDIA Corporationen_IE
dc.contributor.funderScience Foundation Irelanden_IE
dc.contributor.funderIrish Research Councilen_IE
dc.internal.rssid13010821
dc.local.contactPeter Corcoran, Electrical & Electronic Eng, Room 3041, Engineering Building, Nui Galway. 2764 Email: peter.corcoran@nuigalway.ie
dc.local.copyrightcheckedYes
dc.local.versionSUBMITTED
dcterms.projectinfo:eu-repo/grantAgreement/SFI/SFI Strategic Partnership Programme/13/SPP/I2868/IE/Next Generation Imaging for Smartphone and Embedded Platforms/en_IE
nui.item.downloads94


Files in this item

Attribution-NonCommercial-NoDerivs 3.0 Ireland
This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. Please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.

The following license files are associated with this item:

Thumbnail

This item appears in the following Collection(s)

Show simple item record