Co-Training for Visual Object Recognition Based on Self-Supervised Models Using a Cross-Entropy Regularization

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.

Application of Artificial Intelligence in Diagnosis of Craniopharyngioma

“…First, each base classifier is initialized with labeled data, and then the classifier selects the “most confident” unlabeled data, assigns the predicted category of samples and adds them to the labeled data set. The labeled data set is updated and provided to another classifier, and the iterations are repeated until each classifier does not change ( 113 ).…”

Co-Training for Deep Object Detection: Comparing Single-Modal and Multi-Modal Approaches

“…In the latter case, a GAN-based virtual-to-real image translation [ 19 ] is used as pre-processing for the virtual-world images, i.e., before taking them for running the co-training procedure. Very recently, Díaz et al [ 26 ] presented co-training for visual object recognition. In other words, the paper addresses a classification problem, while we address both localization and classification to perform object detection.…”

“…In other words, the paper addresses a classification problem, while we address both localization and classification to perform object detection. While the different views proposed in [ 26 ] rely on self-supervision (e.g., forcing image rotations), here, these rely on data multi-modality. In fact, in our previous work [ 17 ], we used mirroring to force different data views, which can be considered as a kind of self-supervision too.…”

Co-training for Deep Object Detection: Comparing Single-modal and Multi-modal Approaches

“…In the latter case, a GAN-based virtual-to-real image translation [37] is used as pre-processing for the virtualworld images, i.e., before taking them for running the co-training procedure. Very recently, Díaz et al [4] presented co-training for visual object recognition. In other words, the paper addresses a classification problem, while we address both localization and classification to perform object detection.…”

“…In other words, the paper addresses a classification problem, while we address both localization and classification to perform object detection. While the different views proposed in [4] rely on self-supervision (e.g., forcing image rotations), here, these rely on data multi-modality. In fact, in our previous work [28], we used mirroring to force different data views, which can be considered as a kind of self-supervision too.…”