Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Riemannian manifold deep convolutional network image classification method

A deep convolution, network image technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as information loss, performance not increasing but decreasing, and error increasing.

Pending Publication Date: 2022-05-10
YIBIN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the performance of mainstream networks such as ResNet has reached a bottleneck, the room for improvement is limited, and it still does not meet the needs of practical application development.
[0003] The mainstream ResNet adopts the method of adding a residual module in the network, which solves the problem that the performance of the deep network stack does not increase but decreases at a certain level: that is, after the network depth reaches a certain level, the gradient disappears seriously and the error increases. The effect of recognition and classification becomes worse, and the gradient cannot be fed back to the front layer network during backward propagation, resulting in the inability to update the front network parameters
The residual module can increase the depth of the network, but when the depth of the network increases to a certain level (the recognition performance still does not meet the requirements), there will still be a problem of performance degradation
At the same time, another disadvantage of the Riemannian manifold is that it will generate a large amount of information loss. This information loss occurs at multiple levels. The loss mainly comes from convolution operations and downsampling operations.

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
  • Riemannian manifold deep convolutional network image classification method
  • Riemannian manifold deep convolutional network image classification method
  • Riemannian manifold deep convolutional network image classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] figure 1 It is the RM-CNN network structure diagram of the present invention; the mark in RM-CNN: COV refers to the covariance operation module, and AFL refers to the series connection of AvgPool2d and Flatten layers, and its function is to average pool down-sampling and straighten the two-dimensional matrix It is a one-dimensional vector; SAN is a self-attention module; add three modules of COV, AFL, and SAN to the output nodes of conv1, conv2_x, conv3_x, conv4_x, and conv5_x of ResNet in sequence. These three modules are connected in series and connected to the end of ResNet. The output features are directly spliced, and the length of the spliced ​​features is the sum of all features; finally, two SAN modules are connected in series at the end of the network, and the first module is short-circuited;

[0014] Attached below figure 2 The inventive method is described further, and concrete implementation steps are as follows:

[0015] Step 1, pre-train RM-CNN on the l...

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

Aiming at the defects of ResNet series models, the invention provides a Riemannian manifold deep convolutional neural network capable of improving image classification performance, which is called RM-CNN. An RM-CNN image classification model is designed on a ResNet series network, feature correlation on each level is fully utilized, a Riemannian manifold network is adopted to make up for information loss, and meanwhile, a self-attention model is utilized to improve performance; on the whole, the width of the ResNet network is increased, the gradient disappearance problem is solved through the width, and the purpose of improving the image classification performance is achieved.

Description

technical field [0001] The invention relates to the field of image classification, in particular to an image classification method utilizing a Riemannian manifold model fused into a deep convolutional network. Background technique [0002] Image classification technology is widely used in education, aerospace, military and other fields. At present, most images use deep convolutional neural models (such as ResNet, DenseNet) to extract image features, and then identify image content. However, the performance of mainstream networks such as ResNet has reached a bottleneck, the room for improvement is limited, and it still does not meet the needs of practical application development. [0003] The mainstream ResNet adopts the method of adding a residual module in the network, which solves the problem that the performance of the deep network stack does not increase but decreases at a certain level: that is, after the network depth reaches a certain level, the gradient disappears s...

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): G06K9/62G06N3/04G06N3/08G06F17/16G06V10/764
CPCG06N3/08G06F17/16G06N3/045G06F18/241
Inventor 李朝荣
Owner YIBIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products