Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/133257
Share/Export:
logo share SHARE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE

Invite to open peer review
Title

Discriminative learning of deep convolutional feature point descriptors

AuthorsSimo-Serra, Edgar CSIC; Trulls, Eduard CSIC; Ferraz, Luis; Kokkinos, Iasonas; Fua, Pascal; Moreno-Noguer, Francesc CSIC ORCID
Issue Date2015
PublisherInstitute of Electrical and Electronics Engineers
CitationICCV 2015
AbstractDeep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e.g. SIFT. In this paper we use Convolutional Neural Networks (CNNs) to learn discriminant patch representations and in particular train a Siamese network with pairs of (non-)corresponding patches. We deal with the large number of potential pairs with the combination of a stochastic sampling of the training set and an aggressive mining strategy biased towards patches that are hard to classify. By using the L2 distance during both training and testing we develop 128-D descriptors whose euclidean distances reflect patch similarity, and which can be used as a drop-in replacement for any task involving SIFT. We demonstrate consistent performance gains over the state of the art, and generalize well against scaling and rotation, perspective transformation, non-rigid deformation, and illumination changes. Our descriptors are efficient to compute and amenable to modern GPUs, and are publicly available.
DescriptionTrabajo presentado a la International Conference on Computer Vision celebrada en Santiago (España) del 7 al 13 de diciembre de 2015.
Publisher version (URL)http://dx.doi.org/10.1109/ICCV.2015.22
URIhttp://hdl.handle.net/10261/133257
DOI10.1109/ICCV.2015.22
Appears in Collections:(IRII) Comunicaciones congresos




Files in This Item:
File Description SizeFormat
Feature-Point-Descriptors.pdf5,12 MBAdobe PDFThumbnail
View/Open
Show full item record

CORE Recommender

Page view(s)

588
checked on May 18, 2024

Download(s)

374
checked on May 18, 2024

Google ScholarTM

Check

Altmetric

Altmetric


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.