Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/128334
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorTeney, D.en
dc.contributor.authorAnderson, P.en
dc.contributor.authorHe, X.en
dc.contributor.authorVan Den Hengel, A.en
dc.date.issued2018en
dc.identifier.citationProceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018), 2018 / pp.4223-4232en
dc.identifier.isbn9781538664216en
dc.identifier.issn1063-6919en
dc.identifier.issn2575-7075en
dc.identifier.urihttp://hdl.handle.net/2440/128334-
dc.description.abstractDeep Learning has had a transformative impact on Computer Vision, but for all of the success there is also a significant cost. This is that the models and procedures used are so complex and intertwined that it is often impossible to distinguish the impact of the individual design and engineering choices each model embodies. This ambiguity diverts progress in the field, and leads to a situation where developing a state-of-the-art model is as much an art as a science. As a step towards addressing this problem we present a massive exploration of the effects of the myriad architectural and hyperparameter choices that must be made in generating a state-of-the-art model. The model is of particular interest because it won the 2017 Visual Question Answering Challenge. We provide a detailed analysis of the impact of each choice on model performance, in the hope that it will inform others in developing models, but also that it might set a precedent that will accelerate scientific progress in the field.en
dc.description.statementofresponsibilityDamien Teney, Peter Anderson, Xiaodong He, Anton van den Hengelen
dc.language.isoenen
dc.publisherIEEEen
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognitionen
dc.rights© 2018 IEEEen
dc.source.urihttps://ieeexplore.ieee.org/xpl/conhome/8576498/proceedingen
dc.titleTips and tricks for visual question answering: learnings from the 2017 challengeen
dc.typeConference paperen
dc.identifier.rmid0030084426en
dc.contributor.conferenceIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (18 Jun 2018 - 23 Jun 2018 : Salt Lake City, USA)en
dc.identifier.doi10.1109/CVPR.2018.00444en
dc.identifier.pubid367270-
pubs.library.collectionAustralian Institute for Machine Learning publicationsen
pubs.library.teamDS03en
pubs.verification-statusVerifieden
pubs.publication-statusPublisheden
dc.identifier.orcidTeney, D. [0000-0003-2130-6650]en
dc.identifier.orcidVan Den Hengel, A. [0000-0003-3027-8364]en
Appears in Collections:Australian Institute for Machine Learning publications

Files in This Item:
There are no files associated with this item.


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