Image recognition model training method and device and image recognition method and device

An image recognition and training method technology, applied in character recognition, image coding, image data processing, etc., can solve the problems of time-consuming recognition process, inaccurate content, affecting the training efficiency of image recognition model, and image recognition accuracy.

Pending Publication Date: 2019-11-15
BEIJING KINGSOFT DIGITAL ENTERTAINMENT CO LTD +1
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the process of decoding images with the attention mechanism, it often occurs that the same position is repeatedly paid attention to, resulting in a serious time-consuming recognition process and inaccurate generated content, which affects the training efficiency of the image recognition model and image quality. recognition accuracy

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
  • Image recognition model training method and device and image recognition method and device
  • Image recognition model training method and device and image recognition method and device
  • Image recognition model training method and device and image recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the application. However, the present application can be implemented in many other ways different from those described here, and those skilled in the art can make similar promotions without violating the connotation of the present application. Therefore, the present application is not limited by the specific implementation disclosed below.

[0072] Terms used in one or more embodiments of the present application are for the purpose of describing specific embodiments only, and are not intended to limit the one or more embodiments of the present application. As used in one or more embodiments of this application and the appended claims, the singular forms "a", "the", and "the" are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of th...

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 an image recognition model training method and device, and an image recognition method and device, and the method comprises the steps: obtaining a pre-trained image recognitionmodel and training data, wherein the training data comprises a sample image and standard description information corresponding to the sample image; inputting the sample image into the image recognition model, and obtaining description information of the sample image according to an attention adjustment mechanism of the model; and calculating a loss value according to the description information and standard description information corresponding to the sample image, and adjusting model parameters and attention adjustment mechanism parameters of the image recognition model. Through the attentionadjustment mechanism, the image recognition model can effectively pay attention to the local features of the sample image in the process of recognizing the sample image, repeated attention to the same local features of the sample image is avoided, the recognition accuracy of the image recognition model is improved, and the training efficiency of the image recognition model is improved.

Description

technical field [0001] The present application relates to the technical field of machine learning, and in particular to image recognition model training methods and devices, image recognition methods and devices, computing equipment, computer-readable storage media and chips. Background technique [0002] In practical applications, it is often necessary to obtain the description information of the image through the image recognition model, such as identifying the content in the image to generate a table or formula, identifying the content of the image to generate description information, and so on. [0003] When training and using the image recognition model, the encoding-decoding framework is often used, and the content in the image is recognized during the decoding process and combined with the attention mechanism. However, in the process of decoding images with the attention mechanism, it often occurs that the same position is repeatedly paid attention to, resulting in a ...

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): G06K9/62G06T9/00
CPCG06T9/001G06V30/10G06F18/214
Inventor 史红亮廖敏鹏李长亮
Owner BEIJING KINGSOFT DIGITAL ENTERTAINMENT CO LTD
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