Image classification method based on confrontation network generated through feature recalibration

Abstract

The invention discloses an image classification method based on a confrontation network generated through feature recalibration. The image classification method based on the confrontation network generated through feature recalibration is suitable for the field of machine learning and comprises the steps that to-be-classified image data are input into a confrontation network model for network training; a generator and a discriminator which are constituted by a convolutional network are constructed; random noise is initialized and input into the generator; the random noise is subjected to multilevel deconvolution operation in the generator through the convolutional network, and finally, generated samples are obtained; the generated samples and authentic samples are input into the discriminator; and the input samples are subjected to convolution and pooling operation in the discriminator through the convolutional network, thus a feature graph is obtained, a compressed and activated SENetmodule is imported into an intermediate layer of the convolutional network to calibrate the feature graph, thus the calibrated feature graph is obtained, global average pooling is used, and finally,image data classification is output. The SENet module is imported into the intermediate layer of the discriminator, the importance degree of each feature channel is automatically learned, useful features relevant to a task are extracted, features irrelevant to the task are restrained, and thus semi-supervised learning performance is improved.

Description

technical field [0001] The invention relates to an image classification method, and is especially suitable for an image classification method based on feature recalibration generation confrontation network. Background technique [0002] In the training process of a specific network, as the number of iterations increases, the network model often fits well in the training set and the training error is small, but the fitting degree of the test set is not good, resulting in a large test error. Current research shows that ensembles of multiple neural network models often perform better than a single neural network in the validation phase. In essence, it can be understood that the features extracted by different models for the same task are often different. This difference just makes up for the lack of generalization ability between models, so that the final task performance is better than a single model. many. [0003] The integration of discriminative models often combines mod...

AI Technical Summary

Problems solved by technology

[0002] In the training process of a specific network, as the number of iterations increases, the network model often fits well in the training set, and the training error is small, but the fitting degree of the test set is not good, resulting in a large test error.

Images