Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/111362
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorHarwood, B.en
dc.contributor.authorKumar, V.en
dc.contributor.authorCarneiro, G.en
dc.contributor.authorReid, I.en
dc.contributor.authorDrummond, T.en
dc.date.issued2017en
dc.identifier.citationProceedings of the IEEE International Conference on Computer Vision (ICCV 2017), 2017 / vol.2017-October, pp.2840-2848en
dc.identifier.isbn9781538610336en
dc.identifier.issn1550-5499en
dc.identifier.urihttp://hdl.handle.net/2440/111362-
dc.description.abstractTo solve deep metric learning problems and producing feature embeddings, current methodologies will commonly use a triplet model to minimise the relative distance between samples from the same class and maximise the relative distance between samples from different classes. Though successful, the training convergence of this triplet model can be compromised by the fact that the vast majority of the training samples will produce gradients with magnitudes that are close to zero. This issue has motivated the development of methods that explore the global structure of the embedding and other methods that explore hard negative/positive mining. The effectiveness of such mining methods is often associated with intractable computational requirements. In this paper, we propose a novel deep metric learning method that combines the triplet model and the global structure of the embedding space. We rely on a smart mining procedure that produces effective training samples for a low computational cost. In addition, we propose an adaptive controller that automatically adjusts the smart mining hyper-parameters and speeds up the convergence of the training process. We show empirically that our proposed method allows for fast and more accurate training of triplet ConvNets than other competing mining methods. Additionally, we show that our method achieves new state-of-the-art embedding results for CUB-200-2011 and Cars196 datasets.en
dc.description.statementofresponsibilityBen Harwood, Vijay Kumar B G, Gustavo Carneiro, Ian Reid, Tom Drummonden
dc.language.isoenen
dc.publisherIEEEen
dc.relation.ispartofseriesIEEE International Conference on Computer Visionen
dc.rights© 2017 IEEEen
dc.source.urihttp://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8234942en
dc.titleSmart mining for deep metric learningen
dc.typeConference paperen
dc.identifier.rmid0030083145en
dc.contributor.conferenceIEEE International Conference on Computer Vision (ICCV 2017) (22 Oct 2017 - 29 Oct 2017 : Venice, ITALY)en
dc.identifier.doi10.1109/ICCV.2017.307en
dc.publisher.placePiscataway, NJen
dc.relation.granthttp://purl.org/au-research/grants/arc/CE140100016en
dc.relation.granthttp://purl.org/au-research/grants/arc/FL130100102en
dc.identifier.pubid351310-
pubs.library.collectionComputer Science publicationsen
pubs.library.teamDS03en
pubs.verification-statusVerifieden
pubs.publication-statusPublisheden
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]en
Appears in Collections:Computer Science 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.