Co-Training for Visual Object Recognition Based on Self-Supervised Models Using a Cross-Entropy Regularization

Simple item page
datacite.alternateIdentifier.citationENTROPY,Vol.23,,2021
datacite.alternateIdentifier.doi10.3390/e23040423
datacite.creatorDiaz, Gabriel
datacite.creatorPeralta, Billy
datacite.creatorCaro, Luis
datacite.creatorNicolis, Orietta
datacite.date2021
datacite.subject.englishco-training
datacite.subject.englishdeep learning
datacite.subject.englishsemi-supervised learning
datacite.subject.englishself-supervised learning
datacite.subject.english
datacite.titleCo-Training for Visual Object Recognition Based on Self-Supervised Models Using a Cross-Entropy Regularization
dc.date.accessioned2021-10-04T18:54:32Z
dc.date.available2021-10-04T18:54:32Z
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 well-known 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.
dc.identifier.urihttp://repositoriodigital.uct.cl/handle/10925/4349
dc.language.isoen
dc.publisherMDPI
dc.sourceENTROPY
oaire.resourceTypeArticle
uct.indizacionSCI
Files
Collections
MigraciĆ³n Web of Science