Co-Training for Visual Object Recognition Based on Self-Supervised Models Using a Cross-Entropy Regularization |
| |
Authors: | Gabriel Dí az,Billy Peralta,Luis Caro,Orietta Nicolis |
| |
Affiliation: | 1.Departamento de Ciencias de Ingeniería, Facultad de Ingeniería, Universidad Andres Bello, Antonio Varas 880, 8370146 Santiago, Chile; (G.D.); (B.P.);2.Departamento de Ingeniería Informática, Facultad de Ingeniería, Universidad Católica de Temuco, Rudecindo Ortega 2950, 4781312 Temuco, Chile; |
| |
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 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. |
| |
Keywords: | co-training deep learning semi-supervised learning self-supervised learning |
|
|