Semi-supervised image classification method based on generative adversarial network

Abstract

The invention discloses a semi-supervised image classification method based on a generative adversarial network, which mainly solves the problems that the existing unsupervised learning classificationprecision is low and semi-supervised learning needs a large number of accurate labels, and comprises the following implementation steps of: 1) selecting and downloading a standard image training sample and a test sample; 2) setting relevant parameters of network supervised learning, and establishing a generative adversarial network consisting of a generator network, a discriminator network and anauxiliary classifier in parallel; 3) training the generative adversarial network by using a random gradient descent method; and 4) inputting the test sample to be classified into the trained generative adversarial network model, and outputting the category of the image to be detected. The method improves the image classification precision of unsupervised learning, can obtain a very good image classification effect on a sample set only containing a small amount of accurate annotation samples, and can be used for target classification in an actual scene.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a semi-supervised image classification method, which can be used for object classification in actual scenes. Background technique [0002] The main task of image classification is to detect the category of the target in the input image, and then accurately determine the category to which the target belongs. With the continuous deepening of people's understanding of the field of computer vision, image classification has been widely used and developed in this field, and there are already a large number of classification algorithms to realize image classification. The image classification task based on supervised learning with labels has been developed relatively maturely, and better classification accuracy can be obtained on the standard data set, but in actual application scenarios, the training data set of the network is not easy to obtain, for example, in In term...

AI Technical Summary

Problems solved by technology

Although this method realizes the classification of natural images, the disadvantage of this method is that the image features of real images and fake images are extracted in the last layer of neural network, because only unsupervised learning sample set has no Sufficiently accurate training labels make it impossible to accurately find the category boundary, making the classification accuracy not ideal enough to meet the requirements of actual target classification

However, this method still needs 10% of the labeled samples as the training sample set for image classification training. Although it is suitable for the classification of SAR images, it is difficult to obtain a sufficient number of accurately labeled training samples for medical images and natural images, which greatly limits range of application

Images