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

Convolutional neural network training method and system, object classification method and classifier

A technology of convolutional neural network and training method, applied to a method and classifier of object classification, convolutional neural network training method and system field, which can solve the problems of reducing the accuracy of object classification and prone to unbalanced sample distribution

Active Publication Date: 2016-11-16
BEIJING SENSETIME TECH DEV CO LTD
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the distribution of samples in the training sample set used to train CNN is prone to imbalance
Correspondingly, directly using an unbalanced sample set to train a CNN will reduce the accuracy of object classification

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 training method and system, object classification method and classifier
  • Convolutional neural network training method and system, object classification method and classifier
  • Convolutional neural network training method and system, object classification method and classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation manners described herein are only used to explain the present application, rather than to limit the present application. In addition, it should be noted that, for ease of description, only parts relevant to the present application are shown in the drawings. Hereinafter, the present application will be described in detail with reference to the accompanying drawings and in combination with embodiments.

[0041] figure 1 A process 1000 of training a CNN according to an exemplary embodiment of the present application is shown. First, in step S1010, the class (class) containing the number of training samples greater than a predetermined value in the training sample set can be divided into a plurality of sub-categories (cluster), wherein the number of training samples contained in each divid...

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 a convolutional neural network training method and system, an object classification method and a classifier. The convolutional neural network training method comprises the steps of dividing a category with a training sample number greater than a predetermined value in a training sample set into a plurality of sub-categories, wherein a training sample number of each divided sub-category is smaller than or equal to the predetermined value; and training a convolutional neural network according to the divided sub-categories and undivided categories in the training sample set. According to the training method and system, the object classification method and the classifier, the tolerance of a training process to imbalance of the training sample set is enhanced, and correspondingly, the training quality of the CNN (Convolutional Neural Network) and the accuracy of performing object classification by using the CNN are improved.

Description

technical field [0001] The present application relates to the field of deep learning, in particular to a convolutional neural network training method and system, an object classification method and a classifier. Background technique [0002] As a typical representative of deep learning network, CNN (Conventional Neural Network, Convolutional Neural Network) has been more and more widely used in the field of image recognition. Classifying objects is a common operation in the field of image recognition. Traditionally, a pre-classified training sample set is generally used to train a CNN for object classification, and then the trained CNN is used to classify objects, such as binary classification or multi-classification. [0003] However, the distribution of samples in the training sample set used to train CNN is prone to imbalance. Correspondingly, training CNN directly with an unbalanced sample set will reduce the accuracy of object classification. Contents of the inventi...

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): G06K9/62
CPCG06F18/23213G06F18/217G06F18/2415
Inventor 汤晓鸥黄琛李亦宁吕健勤
Owner BEIJING SENSETIME TECH DEV CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com