Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for training image recognition model and image recognition

A technology for identifying models and training images. It is applied in the fields of computer vision, artificial intelligence, and deep learning. It can solve problems such as limitations of expression ability, and achieve the effect of improving practicability, accuracy and generalization performance.

Active Publication Date: 2021-08-31
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF14 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the features used for supervision are still limited in their expressive power because of the small network

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
  • Method and device for training image recognition model and image recognition
  • Method and device for training image recognition model and image recognition
  • Method and device for training image recognition model and image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0022] figure 1 An exemplary system architecture 100 that can be applied to the method for training an image recognition model, the device for training an image recognition model, the method for image recognition or the device for image recognition according to the embodiments of the present application is shown.

[0023] Such as figure 1 As shown, the system architec...

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 provides a method and a device for training an image recognition model and image recognition, and relates to the field of artificial intelligence, in particular to the field of deep learning and computer vision. According to the specific implementation scheme, the method comprises the steps of obtaining a sample set with labels, a sample set without labels and a knowledge distillation network; executing the following training steps: selecting input samples from the sample set with labels and the sample set without labels, and accumulating the number of iterations; respectively inputting the input samples into a student network and a teacher network of the knowledge distillation network, and training the student network and the teacher network; and if the training completion condition is satisfied, selecting an image recognition model from the student network and the teacher network. Through the implementation mode, the manual labeling amount can be reduced, and the performance of the models can be improved.

Description

technical field [0001] The present disclosure relates to the field of artificial intelligence, in particular to the fields of deep learning and computer vision, specifically methods and devices for training image recognition models and image recognition. Background technique [0002] In the field of image classification, there are many more mature methods of knowledge distillation, which basically let the student network learn the soft label output or feature map of the teacher network. However, in the OCR (Optical Character Recognition, Optical Character Recognition) recognition task, the application of knowledge distillation is currently very small. For the CRNN (Convolutional Recurrent Neural Network, Convolutional Recurrent Neural Network) model, the soft label of the student network is directly distilled , the effect is not as high as the accuracy of training directly based on label information. In addition, during distillation, it is generally necessary to have a teac...

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): G06K9/00G06K9/62G06N3/04
CPCG06V30/413G06V30/10G06N3/045G06F18/214G06N3/084G06N3/08G06N3/042
Inventor 郭若愚杜宇宁李晨霞郜廷权赵乔刘其文毕然胡晓光于佃海马艳军
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com