Co-training for visual object recognition based on self-supervised models using a cross-entropy regularization
Loading...
Date
Authors
Díaz, Gabriel
Peralta, Billy M.
Caro, Luis Alberto
Nicolis, Orietta
Peralta, Billy M.
Caro, Luis Alberto
Nicolis, Orietta
Authors
Date
Datos de publicación:
10.3390/e23040423
Keywords
Co-training - Deep Learning - Self-supervised Learning - Semi-supervised Learning
Collections
Abstract
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. © 2021 Elsevier B.V., All rights reserved.
Description
Keywords
Co-training , Deep Learning , Self-supervised Learning , Semi-supervised Learning
Citation
10.3390/e23040423