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

Target recognition model training method and device, equipment and storage medium

A technology for target recognition and model training, applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve problems such as wrongly labeled samples, and achieve the effect of increasing robustness

Active Publication Date: 2020-08-11
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF13 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these labeling schemes inevitably bring a large number of mislabeled samples

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
  • Target recognition model training method and device, equipment and storage medium
  • Target recognition model training method and device, equipment and storage medium
  • Target recognition model training method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

[0021] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0022] figure 1 An exemplary system architecture 100 that can be applied 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 embodiment of the invention discloses a target recognition model training method and device, equipment and a storage medium, and relates to the technical field of artificial intelligence. One specific embodiment of the method comprises the steps: acquiring a training sample set, wherein training samples in the training sample set are labeled target sample images; constructing a first deep convolutional neural network and a second deep convolutional neural network which are different; performing positive and negative sample sampling on the training sample set by using a first deep convolutional neural network and a second deep convolutional neural network to obtain a positive sample set and a negative sample set respectively; and performing cross training on the first deep convolutionalneural network and the second deep convolutional neural network based on the positive sample set and the negative sample set to obtain a target recognition model. According to the embodiment, a weaksupervision target recognition technology based on positive and negative learning is provided, weak supervision learning can be carried out by fully utilizing error annotation samples, and the robustness of the model is improved.

Description

technical field [0001] The embodiments of the present application relate to the technical field of computers, and specifically to the technical field of artificial intelligence. Background technique [0002] Object recognition technology refers to the technology of identifying or comparing objects from images or videos. With the development of artificial intelligence, target recognition is a popular direction of computer vision and digital image processing, which is widely used in many fields such as finance, security, automatic driving, robot navigation, intelligent video surveillance, etc., which greatly facilitates people's life. [0003] Industrial-grade face recognition technology often relies on supervised learning, among which the more mainstream supervised learning methods are supervised learning methods based on softmax and cross-entropy loss functions and their variants, including AM-softmax, L2-softmax, sphereface, arcface, etc. Supervised learning needs to label...

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): G06K9/62G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/172G06N3/045G06F18/23G06F18/214Y02T10/40
Inventor 余席宇张刚韩钧宇
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
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