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

Feature dispersion degree-based attention mechanism method and system

A technology of discreteness and attention, applied in the field of image processing, can solve the problems of losing the importance of features, weakening the importance of features, affecting the redistribution of feature map weights, etc., to achieve the effect of optimizing channel weight distribution and improving performance

Pending Publication Date: 2022-08-09
深圳市爱深盈通信息技术有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, this allocation method does not take into account the influence of the richness (discrete degree) of the feature itself on the effectiveness of recognition, that is, for example, max pooling is used to obtain the maximum value of each channel, but the channel corresponding to the maximum value does not It must have the most effective features for classification, or it may be that there is just a certain feature point in this feature map that has particularity
In the same way, such a method (considering the global maximum or average of the absolute value) sometimes weakens the importance of some high-rich features, such as a feature with a more complex feature shape, that is, the pixel value in the feature has The average pooling method will directly ignore the detail richness of this feature, thus losing the consideration of the importance of this feature and affecting the weight redistribution of the feature map.

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
  • Feature dispersion degree-based attention mechanism method and system
  • Feature dispersion degree-based attention mechanism method and system
  • Feature dispersion degree-based attention mechanism method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present application will be further described in detail below with reference to the accompanying drawings.

[0042] In the embodiments of the present application, in order to optimize the weight distribution of the neural network to the feature map and improve the performance of the neural network in classification and detection, an attention mechanism method and system based on the discrete degree of features are specifically disclosed. refer to figure 1 , is a flow chart of the steps of the attention mechanism method based on the degree of feature discreteness, including:

[0043] S10: Based on the initial feature map, obtain the target variance corresponding to the pixel value in the initial feature map;

[0044] S20: Based on the target variance and the sigmoid activation function, obtain the target weight value;

[0045] S30: Obtain a target feature map based on the target weight value and the initial feature map;

[0046] Among them, in the channel attentio...

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 relates to the technical field of image processing, in particular to a feature dispersion degree-based attention mechanism method and system applied to a convolutional neural network, and the method comprises the steps: obtaining a target variance corresponding to a pixel value in an initial feature map based on the initial feature map; based on the target variance and a sigmoid activation function, obtaining a target weight value; and obtaining a target feature map based on the target weight value and the initial feature map. According to the invention, the weight distribution of the neural network to the feature map can be optimized, so that the performance of the neural network in classification and detection is improved.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular, to a method and system for an attention mechanism based on the degree of discreteness of features applied to a convolutional neural network. Background technique [0002] At present, the weight acquisition method of the existing channel attention mechanism applied to convolutional neural networks usually uses global pooling (max pooling, average pooling or a combination of both) to obtain the mean or maximum value of each channel, so that Each channel has its own weight. Connect these weights to a fully connected layer to finetune the weights, and then use the sigmoid function to normalize them to correspond to the original feature map channels. Multiply to achieve channel weight redistribution to feature maps. [0003] However, this allocation method does not take into account the influence of the richness (discreteness) of the feature itself on the recogni...

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): G06V10/40G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06N3/048
Inventor 申啸尘周有喜
Owner 深圳市爱深盈通信息技术有限公司
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
Eureka Blog
Learn More
PatSnap group products