Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image classification method based on confrontation network generated through feature recalibration

A classification method and feature map technology, applied in biological neural network models, neural learning methods, instruments, etc., can solve the problems of small training error, poor fitting degree of test set, large test error, etc.

Active Publication Date: 2018-11-13
JIANGSU YUNYI ELECTRIC
View PDF10 Cites 74 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image classification method based on confrontation network generated through feature recalibration
  • Image classification method based on confrontation network generated through feature recalibration
  • Image classification method based on confrontation network generated through feature recalibration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The specific embodiment of the present invention will be further described below in conjunction with accompanying drawing:

[0062] Such as figure 1 As shown, the image classification method based on feature recalibration generation confrontation network of the present invention, its steps are:

[0063] S1 constructs a generated confrontational network model, and inputs the image data to be classified into the confrontational network model for network training;

[0064] S2 constructs a generator and a discriminator composed of a convolutional network;

[0065] S3 initializes the random noise, and inputs the random noise into the generator;

[0066] S4 uses the convolutional network in the generator to perform multi-layer deconvolution operations on random noise to finally obtain generated samples;

[0067] S5 will generate samples and input the real samples to the discriminator;

[0068] S6 In the discriminator, the convolutional network is used to perform convoluti...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/24133
Inventor 姜代红黄轲刘其开戴磊
Owner JIANGSU YUNYI ELECTRIC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products