Invariant descriptor learning using a Siamese convolutional neural network

Show simple item record

dc.identifier.uri http://dx.doi.org/10.15488/1176
dc.identifier.uri http://www.repo.uni-hannover.de/handle/123456789/1200
dc.contributor.author Chen, Lin
dc.contributor.author Rottensteiner, Franz
dc.contributor.author Heipke, Christian
dc.date.accessioned 2017-03-02T12:47:57Z
dc.date.available 2017-03-02T12:47:57Z
dc.date.issued 2016
dc.identifier.citation Chen, L.; Rottensteiner, F.; Heipke, C.: Invariant descriptor learning using a Siamese convolutional neural network. In: XXIII ISPRS Congress, Commission III 3 (2016), Nr. 3, S. 11-18. DOI: https://doi.org/10.5194/isprsannals-III-3-11-2016
dc.description.abstract In this paper we describe learning of a descriptor based on the Siamese Convolutional Neural Network (CNN) architecture and evaluate our results on a standard patch comparison dataset. The descriptor learning architecture is composed of an input module, a Siamese CNN descriptor module and a cost computation module that is based on the L2 Norm. The cost function we use pulls the descriptors of matching patches close to each other in feature space while pushing the descriptors for non-matching pairs away from each other. Compared to related work, we optimize the training parameters by combining a moving average strategy for gradients and Nesterov's Accelerated Gradient. Experiments show that our learned descriptor reaches a good performance and achieves state-of-art results in terms of the false positive rate at a 95% recall rate on standard benchmark datasets. eng
dc.language.iso eng
dc.publisher Göttingen : Copernicus GmbH
dc.relation.ispartof 23rd ISPRS Congress, July 12-19 2016, Prague, Czech Republic
dc.relation.ispartofseries XXIII ISPRS Congress, Commission III 3 (2016), Nr. 3
dc.rights CC BY 3.0 Unported
dc.rights.uri https://creativecommons.org/licenses/by/3.0/
dc.subject descriptor learning eng
dc.subject cnn eng
dc.subject siamese architecture eng
dc.subject nesterov's gradient descent eng
dc.subject patch comparison eng
dc.subject image descriptors eng
dc.subject features eng
dc.subject performance eng
dc.subject.ddc 550 | Geowissenschaften ger
dc.title Invariant descriptor learning using a Siamese convolutional neural network
dc.type article
dc.type Text
dc.relation.issn 2194-9034
dc.relation.doi https://doi.org/10.5194/isprsannals-III-3-11-2016
dc.bibliographicCitation.issue 3
dc.bibliographicCitation.volume 3
dc.bibliographicCitation.firstPage 11
dc.bibliographicCitation.lastPage 18
dc.description.version publishedVersion
tib.accessRights frei zug�nglich


Files in this item

The following license files are associated with this item:

This item appears in the following Collection(s):

Show simple item record

 

Search the repository


Browse

My Account

Usage Statistics