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

Gabriel Díaz, Billy Peralta, Luis Caro, Orietta Nicolis

Resultado de la investigación: Contribución a una revistaArtículorevisión exhaustiva

1 Cita (Scopus)

Resumen

Automatic 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.

Idioma originalInglés
Número de artículo423
PublicaciónEntropy
Volumen23
N.º4
DOI
EstadoPublicada - abr 2021

Áreas temáticas de ASJC Scopus

  • Sistemas de información
  • Física matemática
  • Física y astronomía (miscelánea)
  • Ingeniería eléctrica y electrónica

Huella

Profundice en los temas de investigación de 'Co-training for visual object recognition based on self-supervised models using a cross-entropy regularization'. En conjunto forman una huella única.

Citar esto