About: Orthogonal Local Image Descriptors with Convolutional Autoencoders

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Orthogonal Local Image Descriptors with Convolutional Autoencoders Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Orthogonal Local Image Descriptors with Convolutional Autoencoders
Creator	Marchand-Maillet, Stephane Roman-Rangel, Edgar
Source	PMC
abstract	This work proposes the use of deep learning architectures, and in particular Convolutional Autencoders (CAE’s), to incorporate an explicit component of orthogonality to the computation of local image descriptors. For this purpose we present a methodology based on the computation of dot products among the hidden outputs of the center-most layer of a convolutional autoencoder. This is, the dot product between the responses of the different kernels of the central layer (sections of a latent representation). We compare this dot product against an indicator of orthogonality, which in the presence of non-orthogonal hidden representations, back-propagates a gradient through the network, adjusting its parameters to produce new representations which will be closer to have orthogonality among them in future iterations. Our results show that the proposed methodology is suitable for the estimation of local image descriptors that are orthogonal to one another, which is often a desirable feature in many patter recognition tasks.
has issue date	2020-04-29(xsd:dateTime)
bibo:doi	10.1007/978-3-030-49076-8_15
has license	no-cc
sha1sum (hex)	143905effc0a9f5031af955b28d166f1e5841a1f
schema:url	https://doi.org/10.1007/978-3-030-49076-8_15
resource representing a document's title	Orthogonal Local Image Descriptors with Convolutional Autoencoders
has PubMed Central identifier	PMC7297571
schema:publication	Pattern Recognition
resource representing a document's body	covid:143905effc0a9f5031af955b28d166f1e5841a1f#body_text
is schema:about of	named entity 'dot products' named entity 'representation' named entity 'orthogonality' named entity 'For' named entity 'SUITABLE' named entity 'COMPONENT' named entity 'FEATURE' named entity 'DEEP LEARNING' named entity 'PARTICULAR' named entity 'HAVE' named entity 'RESULTS' named entity 'DOT PRODUCT' named entity 'ITERATIONS' named entity 'desirable' named entity 'based' named entity 'closer' named entity 'local' named entity 'estimation' named entity 'computation' named entity 'feature' named entity 'layer' named entity 'autoencoder' named entity 'responses' named entity 'Descriptors' named entity 'dot product' named entity 'orthogonality' named entity 'Image Descriptors' named entity 'methodology' named entity 'glyph' named entity 'Maya culture' named entity 'orthogonality' named entity 'orthogonal bases' named entity 'deep learning' named entity 'convolution' named entity 'convolution' named entity 'autoencoder' named entity 'convolutional layers' named entity 'orthogonality' named entity 'zero-order hold' named entity 'image descriptor' named entity 'convolutional layers' named entity 'image descriptor' named entity 'gradient descent' named entity 'orthogonality' named entity 'up-sampling' named entity 'orthogonality' named entity 'convolutional layer' named entity 'orthogonality' named entity 'local descriptors' named entity 'dot product' named entity 'activation function' named entity 'matrices' named entity 'orthogonality' named entity 'orthogonality' named entity 'orthogonality' named entity 'tensor' named entity 'binary images' named entity 'convolutional layer' named entity 'cross entropy' named entity 'convolutional layer' named entity 'vision problems' named entity 'image retrieval' named entity 'local descriptors' named entity 'binary images' named entity 'activation function' named entity 'orthogonality' named entity 'orthogonality' named entity 'orthogonality' named entity '1, 2' named entity 'tensorflow' named entity 'error function' named entity 'convolution' named entity 'autoencoder' named entity 'orthogonality' named entity 'regularizer' named entity 'glyph' named entity 'orthogonal' named entity 'orthogonal' named entity 'cross entropy' named entity 'orthogonal' named entity 'convolution' named entity 'local descriptors'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software