A training method of an alignment classification model and an image classification method

A technology for classifying models and training images, applied in the field of deep learning, which can solve the problems of unstable dog face detection, affecting the accuracy of predicted dog face points, etc.

Active Publication Date: 2019-06-18
XIAMEN MEITUZHIJIA TECH
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the variety of dogs and their lively nature, dog face detection is unstable, which affects the accuracy of predicting dog face points.

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
  • A training method of an alignment classification model and an image classification method
  • A training method of an alignment classification model and an image classification method
  • A training method of an alignment classification model and an image classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0031] figure 1 is a block diagram of an example computing device 100 . In a basic configuration 102 , computing device 100 typically includes system memory 106 and one or more processors 104 . A memory bus 108 may be used for communication between the processor 104 and the system memory 106 .

[0032] Depending on the desired configuration, processor 104 may be any type of processor including, but not limited to, a microprocesso...

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 of an alignment classification model, the alignment classification model comprises a main network, a first branch network and a second branch network, the method comprises the following steps: obtaining an annotated training image, the training image having corresponding annotation data, and the annotation data comprising an image category; Inputting the training image into a classification model for training to obtain a trained second branch network; And inputting the training image into the alignment classification model for training, and optimizingthe second branch network to obtain a trained alignment classification model. According to the scheme, the model classification precision can be improved, and the model training time and the requireddata size are saved.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a training method for an alignment classification model, an image classification method, a computing device and a storage medium. Background technique [0002] Cat and dog face classification has a wide range of application scenarios. For example, in the process of taking pictures of cats and dogs, by distinguishing between cats and dogs, some customized animation controls are added to increase the user's shooting fun. However, the traditional cat and dog face classification training method requires a huge amount of training data and a complex network structure, which cannot meet the requirements of mobile terminals for data size and training speed. On the one hand, for image classification, it takes a lot of time to retrain a complete network; on the other hand, existing classification models mainly use deep convolutional networks such as VGG to extract features fr...

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): G06K9/62G06K9/66G06N3/04G06N3/08
Inventor 许益鸿齐子铭涂清华李志阳张伟
Owner XIAMEN MEITUZHIJIA TECH
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