Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Conference paper
Title: Learning local image descriptors with deep siamese and triplet convolutional networks by minimizing global loss functions
Author: Vijay Kumar, B.
Carneiro, G.
Reid, I.
Citation: Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, vol.2016-December, pp.5385-5394
Publisher: IEEE
Issue Date: 2016
Series/Report no.: IEEE Conference on Computer Vision and Pattern Recognition
ISBN: 9781467388511
ISSN: 1063-6919
Conference Name: 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) (26 Jun 2016 - 1 Jul 2016 : Las Vegas, NV)
Statement of
Vijay Kumar B G, Gustavo Carneiro, Ian Reid
Abstract: Recent innovations in training deep convolutional neural network (ConvNet) models have motivated the design of new methods to automatically learn local image descriptors. The latest deep ConvNets proposed for this task consist of a siamese network that is trained by penalising misclassification of pairs of local image patches. Current results from machine learning show that replacing this siamese by a triplet network can improve the classification accuracy in several problems, but this has yet to be demonstrated for local image descriptor learning. Moreover, current siamese and triplet networks have been trained with stochastic gradient descent that computes the gradient from individual pairs or triplets of local image patches, which can make them prone to overfitting. In this paper, we first propose the use of triplet networks for the problem of local image descriptor learning. Furthermore, we also propose the use of a global loss that minimises the overall classification error in the training set, which can improve the generalisation capability of the model. Using the UBC benchmark dataset for comparing local image descriptors, we show that the triplet network produces a more accurate embedding than the siamese network in terms of the UBC dataset errors. Moreover, we also demonstrate that a combination of the triplet and global losses produces the best embedding in the field, using this triplet network. Finally, we also show that the use of the central-surround siamese network trained with the global loss produces the best result of the field on the UBC dataset.
Rights: © 2016 IEEE
DOI: 10.1109/CVPR.2016.581
Grant ID:
Appears in Collections:Aurora harvest 8
Computer Science publications

Files in This Item:
File Description SizeFormat 
  Restricted Access
Restricted Access1.39 MBAdobe PDFView/Open

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