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

Network model training method, image recognition method and related devices

A network model and training method technology, applied in the field of deep learning, can solve the problems of low efficiency of model update, excessive computing resources, consumption, etc.

Pending Publication Date: 2022-04-12
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for large-scale samples, re-extracting the embedding features of all samples will consume more computing resources, resulting in low model update efficiency

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
  • Network model training method, image recognition method and related devices
  • Network model training method, image recognition method and related devices
  • Network model training method, image recognition method and related devices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0103]Embodiments of the present application provide a network model training method, an image recognition method, and related devices. This application can achieve the effect of optimizing the badcase while keeping the characteristics of the goodcase close. Therefore, when training the model, there is no need to re-extract all image samples to extract embedded features, thus saving computing resources.

[0104] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and not necessarily Used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the application described herein, for example, can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "corresponding to" and an...

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 network model training method realized based on a deep learning technology. The method comprises the following steps: acquiring an original image sample pair set and a newly added image sample pair set; according to the newly added image sample pair set, obtaining a labeling result of each original image sample pair in the original image sample pair set, and obtaining an expanded image sample pair set; constructing a triple image sample set according to the expanded image sample pair set and the newly added image sample pair set; obtaining a target embedding feature corresponding to each sample image in each triple image sample through a to-be-trained network model; and according to the labeling result corresponding to each image sample and the target embedding feature corresponding to each sample image, updating model parameters of the to-be-trained network model. The invention also provides an image recognition method and a related device. According to the method, when the model is trained, all image samples do not need to be re-extracted to extract embedded features, so that computing resources are saved.

Description

technical field [0001] The present application relates to the field of deep learning, and in particular to a network model training method, an image recognition method and related devices. Background technique [0002] With the continuous development of artificial intelligence (AI) technology, image recognition based on deep learning has become the main method in the current image recognition field. Deep learning can automatically extract and classify similar features from different images, which promotes the development of image recognition, and unsupervised learning has become a hot spot in the field of deep learning. [0003] At present, after the trained model is put into application, there may be wrongly identified (badcase) sample pairs, and these badcase sample pairs are not used in the training process. Therefore, after accumulating a certain number of badcase sample pairs, these badcase sample pairs can be used to retrain the model, so as to better support the embe...

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): G06F16/583G06V10/75G06V10/762G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
Inventor 郭卉
Owner TENCENT TECH (SHENZHEN) CO LTD