An image classification method and device
An image and attention technology, applied in the field of image recognition, can solve the problem of low image classification efficiency and accuracy, and achieve the effects of improving efficiency and accuracy, improving training efficiency and shortening training time.
Active Publication Date: 2021-01-15
NAT UNIV OF DEFENSE TECH
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In view of this, the purpose of one or more embodiments of this specification is to propose an image classification method and equipment to solve the problem of low image classification efficiency and accuracy
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0039] In order to make the purpose, technical solutions and advantages of this specification more clear, the following will further describe this specification in detail in combination with specific embodiments and with reference to the accompanying drawings.
[0040] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present specification shall have ordinary meanings understood by those skilled in the art to which the present disclosure belongs. "First", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Comprising" or "comprising" and similar words mean that the elements, objects or method steps appearing before the word cover the elements, objects or method steps listed after the word and their equivalents, without excluding other elements, objects or method steps. Method steps. Words such ...
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
Login to View More Abstract
An image classification method and device provided by one or more embodiments of this specification, including: establishing a residual network model, replacing the standard convolution in the original side diameter of the residual network model with a hole convolution, and generating a hole The residual network backbone; based on the channel attention module and the spatial attention module of the attention mechanism model, the weight layer of the residual network model is generated; the residual composed of the hollow residual network backbone and the weight layer is generated An attention mechanism model, training the residual attention mechanism model; inputting image data into the residual attention mechanism model, and identifying and classifying the image data. One or more embodiments of this specification integrate the residual mechanism into the attention model, and combine the context information inside the attention mechanism without adding parameters, so as to help the attention model extract the information of interest in the image classification task more accurately. features, thereby improving the efficiency and accuracy of image classification.
Description
technical field [0001] One or more embodiments of this specification relate to the technical field of image recognition, and in particular, to an image classification method and device. Background technique [0002] With the improvement of social informatization, images have gradually replaced text as an important carrier for human transmission and storage of information. The disorder and huge volume of information contained in images pose a huge challenge to the processing of image information. How to effectively classify images to extract the useful information we need has become a topic of much concern in the field of computer vision. [0003] However, with the development of society, the amount of image data is increasing exponentially, and the scope of application is constantly expanding. The network structure and algorithm of image classification in the existing technology are far from perfect and efficient for different types, different natures and disorderly images....
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06K9/46G06N3/04
CPCG06V10/44G06N3/048G06N3/045G06F18/24G06F18/214
Inventor 蒋杰杨君燕许辉孙家豪刘阳康来魏迎梅谢毓湘
Owner NAT UNIV OF DEFENSE TECH