Co-training for visual object recognition based on self-supervised models using a cross-entropy regularization

Vista sencilla de ítem
dc.contributor.authorDíaz, G.
dc.contributor.authorPeralta, B.
dc.contributor.authorCaro, L.
dc.contributor.authorNicolis, O.
dc.date.accessioned2021-05-14T21:55:28Z
dc.date.available2021-05-14T21:55:28Z
dc.date.issued2021-04
dc.descriptionIndexación Scopuses
dc.description.abstractAutomatic recognition of visual objects using a deep learning approach has been successfully applied to multiple areas. However, deep learning techniques require a large amount of labeled data, which is usually expensive to obtain. An alternative is to use semi-supervised models, such as co-training, where multiple complementary views are combined using a small amount of labeled data. A simple way to associate views to visual objects is through the application of a degree of rotation or a type of filter. In this work, we propose a co-training model for visual object recognition using deep neural networks by adding layers of self-supervised neural networks as intermediate inputs to the views, where the views are diversified through the cross-entropy regularization of their outputs. Since the model merges the concepts of co-training and self-supervised learning by considering the differentiation of outputs, we called it Differential Self-Supervised Co-Training (DSSCo-Training). This paper presents some experiments using the DSSCo-Training model to wellknown image datasets such as MNIST, CIFAR-100, and SVHN. The results indicate that the proposed model is competitive with the state-of-art models and shows an average relative improvement of 5% in accuracy for several datasets, despite its greater simplicity with respect to more recent approaches. © 2020 by the authors.es
dc.description.urihttps://www.mdpi.com/1099-4300/23/4/423
dc.identifier.citationEntropy, Volume 23, Issue 4, April 2021, Article number 423es
dc.identifier.doi10.3390/e23040423
dc.identifier.issn10994300
dc.identifier.urihttp://repositorio.unab.cl/xmlui/handle/ria/18858
dc.language.isoenes
dc.publisherMDPI AGes
dc.subjectObject Detectiones
dc.subjectCNNes
dc.subjectIOUes
dc.subjectDeep learninges
dc.subjectSelf-supervised learninges
dc.subjectSemi-supervised learninges
dc.titleCo-training for visual object recognition based on self-supervised models using a cross-entropy regularizationes
dc.typeArtículoes
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Diaz_G_Co-trainin_2021.pdf
Tamaño:
544.79 KB
Formato:
Adobe Portable Document Format
Descripción:
TEXTO COMPLETO EN INGLÉS
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
1.71 KB
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar
Colecciones
FIng - Artículos de Revista