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

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. © 2020 by the authors.

Notas

Indexación Scopus

Palabras clave

Object Detection, CNN, IOU, Deep learning, Self-supervised learning, Semi-supervised learning

Citación

Entropy, Volume 23, Issue 4, April 2021, Article number 423

DOI

10.3390/e23040423

URI

http://repositorio.unab.cl/xmlui/handle/ria/18858

Colecciones

FIng - Artículos de Revista

Página completa del ítem