Image classification method and device based on semi-supervised deep learning and storage medium

Abstract

The invention discloses an image classification method and device based on semi-supervised deep learning and a storage medium. The method includes: acquiring label training image samples and non-labeltraining image samples, and obtaining a label training set; combining deep learning and semi-supervised learning to carry out training of a convolutional neural network (CNN) on the label training set, and establishing a unified model of semi-supervised deep learning and unlabeled-sample class estimation; and carrying out image recognition / classification on the basis of the model of semi-supervised deep learning and unlabeled sample class estimation. According to the method, distinguishing information hidden in non-label training data can be utilized, high separability of current deep features can also be utilized at the same time, the unlabeled samples can be more efficiently and accurately utilized, and thus better image recognition performance can be obtained.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to an image classification method, device and storage medium based on semi-supervised deep learning. Background technique [0002] In recent years, technologies based on deep learning (Deep Learning) have achieved good results in the field of computer vision, such as face recognition and target classification. Representative deep learning methods include CNN (convolutional neural network), RNN (Recurrent Neural Network), Autoencoder, GAN (Generative Adversarial Network), etc. [0003] However, in practical applications, since it takes a lot of time and manpower to label samples, in real life, there are usually a large number of unlabeled samples, and these unlabeled samples are used to improve the final recognition effect The method is called semi-supervised learning. [0004] In order to make better use of the discriminative information of unlabeled training dat...

AI Technical Summary

Problems solved by technology

Although the method of semi-supervised deep learning can learn high-level representation features, it ignores how to more effectively utilize the high discriminative properties of unlabeled samples.

Images