Model generation method, target detection method, device, electronic equipment and medium

A target detection and model generation technology, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve the problem of poor generalization performance of target detection models, and achieve the effect of improving generalization performance

Pending Publication Date: 2021-01-22
BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the existing technology has the following technical problems

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
  • Model generation method, target detection method, device, electronic equipment and medium
  • Model generation method, target detection method, device, electronic equipment and medium
  • Model generation method, target detection method, device, electronic equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] figure 1 It is a flowchart of a model generation method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of improving the generalization performance of the target detection model, especially suitable for the situation of improving the generalization performance of the target detection model without increasing the cost of manual labeling. The method can be executed by the model generation device provided by the embodiment of the present invention, the device can be realized by software and / or hardware, and the device can be integrated on an electronic device, which can be various user terminals or servers.

[0041] see figure 1 , the method of the embodiment of the present invention specifically includes the following steps:

[0042] S110. Based on multiple sets of teacher training samples including the first sample image and sample labeling results of known objects in the first sample image, train the original detection...

Embodiment 2

[0060] figure 2 It is a flow chart of a model generation method provided in Embodiment 2 of the present invention. This embodiment is optimized on the basis of the above-mentioned technical solutions. In this embodiment, optionally, the student network having the same network type as the teacher network includes a target prediction module and a loss calculation module; for each group of first training samples, based on multiple groups of first training samples having the same The network type student network is trained, which may specifically include: inputting the first sample image into the target prediction module to obtain the first prediction result; inputting the first detection result and the first prediction result into the loss calculation module, and according to The output of the loss calculation module adjusts the network parameters in the target prediction module. Wherein, explanations of terms that are the same as or corresponding to the above embodiments are ...

Embodiment 3

[0084] image 3 It is a flow chart of a model generation method provided in Embodiment 3 of the present invention. This embodiment is optimized based on the technical solutions in the second embodiment above. In this embodiment, optionally, adjusting the network parameters in the target prediction module according to the output result of the loss calculation module may specifically include: determining the loss coefficient according to the pre-output result and the value range of the loss, wherein the pre-output result is the pre-assessment of the student The output result of the loss calculation module after the iterative training of the network for a preset number of times; according to the loss coefficient and the output result of the loss calculation module after the first detection result and the first prediction result are input to the loss calculation module, adjust the target prediction module. Network parameters. Wherein, explanations of terms that are the same as o...

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 model generation method, a target detection method, a device, electronic equipment and a medium. The model generation method comprises the steps of trainingan original detection model based on multiple groups of teacher training samples including a first sample image and a sample labeling result of a known target in the first sample image to obtain a teacher network; taking the first sample image and a first detection result obtained after the first sample image is input into a teacher network as a first training sample, and taking the second sampleimage and a second detection result obtained after the second sample image is input into the teacher network as a second training sample; and training a student network having the same network type as the teacher network based on the plurality of groups of first training samples and the plurality of groups of second training samples to generate a target detection model. According to the technicalscheme provided by the embodiment of the invention, the effect of improving the generalization performance of the target detection model is achieved under the condition of not additionally increasingthe manual annotation cost.

Description

technical field [0001] Embodiments of the present invention relate to the field of computer application technologies, and in particular, to a model generation method, a target detection method, a device, electronic equipment, and a medium. Background technique [0002] With the popularization of artificial intelligence technology, computer vision technology based on deep learning is becoming more and more popular. The importance of target detection as the basic research of computer vision technology is self-evident. [0003] Specifically, target detection is a pre-step for visual analysis. Applications such as face recognition and pedestrian re-recognition need to detect faces or human bodies first, and then perform subsequent recognition on the detected faces or human bodies. Obviously, target detection is an extremely important part of artificial intelligence when it lands in the industry. [0004] However, the prior art has the following technical problems: the generaliz...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V2201/07G06N3/045G06F18/214
Inventor 程鹏何凌霄廖星宇王林芳刘武梅涛
Owner BEIJING WODONG TIANJUN INFORMATION TECH 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