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

Image sample data enhancement training method and device and electronic equipment

A technology of image samples and training methods, which is applied in the fields of artificial intelligence, image recognition and deep learning, and computer vision. It can solve problems such as the inability to improve the model to solve difficult samples, the small number of difficult samples, and the unbalanced training of easy samples and difficult samples.

Pending Publication Date: 2022-06-07
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, the number of difficult samples obtained through the existing methods is small, the training of easy samples and difficult samples is unbalanced, and the ability of the model to solve difficult samples cannot be improved.

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 sample data enhancement training method and device and electronic equipment
  • Image sample data enhancement training method and device and electronic equipment
  • Image sample data enhancement training method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] According to the embodiments of the present disclosure, an embodiment of an image sample data enhancement training method is provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, Also, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that herein.

[0038] figure 1 is a flowchart of the image sample data augmentation training method according to the first embodiment of the present disclosure, such as figure 1 As shown, the method includes the following steps:

[0039] Step S102, acquiring samples to be trained.

[0040] In step S102, the to-be-trained sample is composed of multiple images, and the multiple images at least contain posture information of the target object. For example, the sample to be trained may be an image dataset, and the target ob...

Embodiment 2

[0059] According to an embodiment of the present disclosure, an embodiment of an image sample data augmentation training method is also provided.

[0060] Specifically, before performing data enhancement on the image samples, the electronic device needs to acquire the samples to be trained, wherein the electronic device can acquire the samples to be trained based on random numbers. Specifically, electronic equipment can be figure 2 The method shown to obtain the samples to be trained, by figure 2 It can be seen that the method includes the following steps:

[0061] Step S202, obtaining a preset random number;

[0062] Step S204, when the random number is less than the random number threshold, obtain the sample to be trained from the training sample library;

[0063] Step S206, when the random number is greater than or equal to the random number threshold, obtain the sample to be trained from the target queue.

[0064] Optionally, the electronic device may establish a ran...

Embodiment 3

[0092] According to an embodiment of the present disclosure, an embodiment of an image sample data augmentation training method is also provided.

[0093] Specifically, before performing data enhancement on the image samples, the electronic device first obtains the samples to be trained, and then uses the samples to be trained to train the preset keypoint model, and obtains the first loss value corresponding to the training result, and then according to the first loss value A loss value updates at least one training sample included in the preset queue to obtain a target queue, and calculates a second loss value of at least one training sample included in the target queue, and then determines at least one training sample from the target queue according to the second loss value. For a candidate training sample, when the third loss value corresponding to any one or more candidate training samples satisfies the preset condition, the candidate training sample can be determined as 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 sample data enhancement training method and device and electronic equipment, and relates to the field of artificial intelligence, in particular to the technical field of computer vision, image recognition and deep learning. According to the specific implementation scheme, a to-be-trained sample is obtained, the to-be-trained sample is adopted to train a preset key point model, and a first loss value corresponding to a training result is obtained, so that at least one training sample contained in a preset queue is updated according to the first loss value, and a target queue is obtained, at least part of training samples in the to-be-trained samples are stored in the preset queue, then a second loss value of at least one training sample contained in the target queue is calculated, and at least one candidate training sample is determined from the target queue according to the second loss value; and finally, when the third loss value corresponding to any one or more candidate training samples meets a preset condition, determining the candidate training sample as a target training sample.

Description

technical field [0001] The present disclosure relates to the field of artificial intelligence, and in particular, to the technical fields of computer vision, image recognition and deep learning. Specifically, the present disclosure provides an image sample data enhancement training method, apparatus, and electronic device. Background technique [0002] With the development of artificial intelligence technology, human pose estimation technology based on deep learning has been increasingly applied to scenes such as human action classification. At the same time, with the improvement and implementation of various deep learning algorithms, the estimation accuracy of human key points It is also getting higher and higher, but in the process of actual human pose estimation, it will also encounter some difficult samples that are difficult to solve. For example, interfering scenes such as human body truncation and human occlusion overlap will greatly reduce the performance of deep lea...

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
IPC IPC(8): G06V40/20G06V10/46G06V10/774G06K9/62G06N20/00
CPCG06N20/00G06F18/214
Inventor 卢子鹏王健孙昊丁二锐
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