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

Training method and device of student model for image processing

A student model and image processing technology, applied in the field of knowledge distillation, can solve problems such as poor search results

Active Publication Date: 2021-01-05
SHANGHAI YITU NETWORK SCI & TECH
View PDF14 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a training method and device for a student model used in image processing to solve the problem of poor search effect in the related art of using the teacher model training student model

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
  • Training method and device of student model for image processing
  • Training method and device of student model for image processing
  • Training method and device of student model for image processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] In order to solve the problem in the related art that the search effect of the student model trained by the teacher model is relatively poor, the embodiment of the present application provides a training method and device for the student model used in image processing.

[0057] The preferred embodiments of the application will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the application, and are not used to limit the application, and in the absence of conflict, the application The embodiments and the features in the embodiments can be combined with each other.

[0058] In related technologies, knowledge distillation is still in the academic research stage, and the various distillation methods given do not consider the actual business scenarios, and in different business scenarios, the key knowledge that the student model needs to learn from t...

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 training method and device for a student model for image processing, and belongs to the technical field of knowledge distillation, and the method comprises the steps: obtaining the parameters of a classification layer in a teacher model which is obtained through the classification training of target objects in a plurality of image samples, initializing parameters of a classification layer in a to-be-trained student model by utilizing the obtained parameters, inputting at least part of the image samples into the student model for classification, and adjusting parameters of a target layer in front of the classification layer in the student model according to a classification loss value of the student model, and enabling the image features of each type of target objects learned by the target layer in the student model to approach the image features of the type of target objects learned by the target layer in the teacher model, and ending the training until it isdetermined that the classification error of the student model is smaller than a set error, wherein the teacher model and the student model each comprise a convolution layer, a classification layer anda normalization layer which are connected in sequence, and the normalization layers of the teacher model and the student model use the same normalization function.

Description

technical field [0001] The present application relates to the technical field of knowledge distillation, in particular to a method and device for training a student model for image processing. Background technique [0002] In general, the important role of knowledge distillation is to transfer the knowledge learned by the complex model to the lightweight model, so that the lightweight model can have similar performance to the complex model when the original parameters are small. Among them, Complex models are often called teacher models, and lightweight models are often called student models. [0003] Take, for example, the classification of target objects in image samples. In related technologies, the teacher model is first trained with a large number of image samples and the labeled categories of target objects in the image samples. When the classification accuracy of the teacher model meets the requirements, the teacher model is then used to The output results are used ...

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): G06Q50/20G06K9/00G06K9/46G06K9/62
CPCG06Q50/205G06V40/16G06V10/40G06F18/213G06F18/24G06F18/214
Inventor 史维东任广辉陈云鹏
Owner SHANGHAI YITU NETWORK SCI & TECH
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