PlumX Metrics
Embed PlumX Metrics

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

Entropy, ISSN: 1099-4300, Vol: 23, Issue: 4
2021
  • 9
    Citations
  • 0
    Usage
  • 10
    Captures
  • 1
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

Article Description

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.

Bibliographic Details

Díaz, Gabriel; Peralta, Billy; Caro, Luis; Nicolis, Orietta

MDPI AG

Computer Science; Mathematics; Physics and Astronomy; Engineering

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know