Image classification method, training method of image classification model and equipment

A classification method and classification model technology, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve the problems of complex data, high cost of sample data labeling, and few data set labels, so as to improve the classification effect , good learning effect, pay attention to the effect of continuity

Pending Publication Date: 2021-10-01
山东幻科信息科技股份有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, due to the complexity of sample data in some application image fields (such as the medical image field), professionals are required to label, resulting in a huge cost of sampl

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, training method of image classification model and equipment
  • Image classification method, training method of image classification model and equipment
  • Image classification method, training method of image classification model and equipment

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0058] Example one

[0059] This embodiment proposes an image classification method. figure 1 It is a flow chart of an image classification method according to an embodiment of the present invention. like figure 1 As shown, the method includes S10-S30.

[0060] S10: Separate the image to be classified into multiple patches, generate each PATCH corresponding to the PATCH vector; to reduce each PATCH vector through the linear layer, a plurality of downthetted PATCH vectors are spliced ​​to obtain the first sequence vector; A variable vector is embedded in the first sequence vector, where the second sequence vector is obtained, wherein the variable vector is the same as that of each reduced PATCH vector size, and the variable vector corresponds to the more The PATCH that is mostly representative of the characteristics of the image to be classified.

[0061] Alternatively, the image to be classified is divided into a plurality of patches, and a sequence is paved, followed by a downtim...

Example Embodiment

[0087] Example 2

[0088] This embodiment provides a training method of an image classification model for training the image classification model constituted by the image classification method described in the first embodiment. figure 2 It is a flow chart of a training method for an image classification model provided by the embodiment of the present invention. like figure 2 As shown, the method includes steps S01-S06.

[0089] S01: Get a training data set D, where the training data set includes a label data set D. l And label data set D u Each training data is a training image, each with label data D l Label D l Real category Y l .

[0090] S02: For each label data d l Enhanced random data is enhanced, and there is a label data set after enhancement For each label Data D u Enhanced the random data of K, get K enhanced label data set K = 1, ..., k, all D u K And collect Put each label Data D u K The image classification model corresponding to the image classification method a...

Example Embodiment

[0125] Example three

[0126] Figure 4 It is a flow chart of another image classification method according to an embodiment of the present invention. This method implements the network learning process of image classification based on Transformer's semi-regulatory algorithm, including training phase and prediction stages. like Figure 4 As shown, the method includes S1-S8.

[0127] S1: Predict the pseudo label. First, all non-tagged data is enhanced, repeat K times, and then predict the enhanced label data input model, obtain K pseudo tags, and finally take an average operation as a pseudo-label without label data.

[0128] S2: Image block processing. The input image is cut into multiple patches, and a sequence is paved, followed by a reduced operation by the learning linear projection. Finally, the first sequence of sequences corresponding to all PATCH is embedded in a vector (referred to as "Patch Embed Retide Vector). This vector initialization is random, learning (ie, variable...

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, a training method of an image classification model and equipment. The image classification method comprises the following steps: segmenting a to-be-classified image into a plurality of patches, and performing dimensionality reduction on each patch vector through a linear layer to obtain a first sequence vector; embedding a variable vector into the head of the first sequence vector to obtain a second sequence vector; initializing a position coding vector of the second sequence vector, and embedding the initialized position coding vector into the second sequence vector to obtain an input vector; inputting the input vector into an encoder of a Transform model to obtain an encoding vector; taking a variable vector of the head part of the encoding vector as a feature vector of the to-be-classified image; and inputting the feature vector into a classifier of a Transform model to obtain a prediction category probability of the to-be-classified image. According to the invention, the classification effect of image classification is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image classification, and in particular to an image classification method, a training method and equipment for an image classification model. Background technique [0002] In the field of image recognition and classification, deep learning within the scope of machine learning is an effective method, which has produced many excellent algorithms and networks, including the common convolutional neural network (Convolutional Neural Network, referred to as "CNN"), loop Four mainstream network structures: Recurrent Neural Network, Generative Adversarial Networks, and Reinforcement learning. [0003] However, due to the complex sample data in some application image fields (such as the medical image field), professionals are required to label, resulting in a huge cost of sample data labeling, and it is not easy to obtain a large amount of labeling data. There are few labels in the image dat...

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
IPC IPC(8): G06K9/62G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/213G06F18/2415
Inventor 张凯王瑞丰丁冬睿杨光远逯天斌王潇涵
Owner 山东幻科信息科技股份有限公司
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap