Convolutional-neural-network learning method of multi-scale progressive accumulation

A convolutional neural network and learning method technology, applied in the fields of machine vision and artificial intelligence, can solve problems such as integration and large amount of calculation, achieve the effects of increasing complexity, improving feature learning ability, and saving calculation amount

Active Publication Date: 2018-11-23
HUAQIAO UNIVERSITY
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It can be seen that the algorithm in [2] fails to integrate the image downsampling operation into the learning of the convolutional neural network, and it actually needs to train multiple convolutional neural networks at the same time, and the amount of calculation is too large

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
  • Convolutional-neural-network learning method of multi-scale progressive accumulation
  • Convolutional-neural-network learning method of multi-scale progressive accumulation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention discloses a convolutional neural network learning method with multi-scale gradual accumulation, which adopts the mean value pooling operation to construct a multi-scale image pyramid for input images; then, images of different scales are gradually sent into the convolutional neural network, so that With the gradual deepening of the network depth, the convolutional neural network can learn and gradually accumulate features on a variety of images of different scales, which improves the feature learning ability of the convolutional neural network.

[0022] like figure 1 As shown, a kind of convolutional neural network learning method of multi-scale step-by-step accumulation of the present invention, the specific steps are as follows:

[0023] Step 1. A fast algorithm based on Average Pooling (AP) operation is used to construct a multi-scale image pyramid.

[0024] For the input image, filter the noise through the mean low-pass filter, and then obtain...

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 a convolutional-neural-network learning method of multi-scale progressive accumulation. The method can be widely applied to the fields of machine vision and artificial intelligence such as target detection, target classification and target recognition. Firstly, average pooling operations are employed by the method to construct a multi-scale image pyramid on input images; and then images of different scales are progressively sent into a convolutional neural network, the convolutional neural network is enabled to carry out learning on the multiple images of the differentscales with progressive increasing of network depth and carry out progressive feature accumulation, and thus feature learning ability of the convolutional neural network is improved.

Description

technical field [0001] The invention relates to the fields of machine vision and artificial intelligence, in particular to a multi-scale progressively cumulative convolutional neural network learning method, which can be applied to target detection, target classification and target recognition systems. Background technique [0002] Convolutional neural network is currently the most popular deep learning algorithm. In recent years, a large number of target detection, target classification and target recognition algorithms based on convolutional neural networks have emerged. The accuracy of these algorithms largely depends on the feature learning ability of convolutional neural networks. [0003] At present, most of the research on convolutional neural networks focuses on improving the feature learning ability by deepening the network depth. Many extremely deep convolutional neural networks have emerged, such as GoogleNet, ResNet, DenseNet, etc. These extremely deep convoluti...

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): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 朱建清曾焕强陈婧蔡灿辉杜永兆吴含笑
Owner HUAQIAO UNIVERSITY
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