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

Gabriel Díaz, Billy Peralta, Luis Caro, Orietta Nicolis

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

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.

Original languageEnglish
Article number423
JournalEntropy
Volume23
Issue number4
DOIs
Publication statusPublished - Apr 2021

Keywords

  • Co-training
  • Deep learning
  • Self-supervised learning
  • Semi-supervised learning

ASJC Scopus subject areas

  • Information Systems
  • Mathematical Physics
  • Physics and Astronomy (miscellaneous)
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Co-training for visual object recognition based on self-supervised models using a cross-entropy regularization'. Together they form a unique fingerprint.

Cite this