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

Neural network structure search method applied to picture multi-attribute prediction

A network structure and neural network technology, applied in the field of neural network structure search, can solve problems such as lack of generalization ability of different tasks, achieve a wide range of practical application value, ensure robustness, and reduce the effect of design and adjustment

Inactive Publication Date: 2018-12-21
ZHEJIANG UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method mainly has the following problems: 1) Usually the structure of the deep neural network is designed by experts based on domain-specific expertise, which lacks the ability to generalize to different tasks. The structure of the neural network; 2) The designer needs to have rich experience in neural network design and parameter adjustment. A good neural network structure usually requires careful adjustment by the designer. This process will cost the designer a lot of time and energy

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
  • Neural network structure search method applied to picture multi-attribute prediction
  • Neural network structure search method applied to picture multi-attribute prediction
  • Neural network structure search method applied to picture multi-attribute prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0037] On the contrary, the invention covers any alternatives, modifications, equivalent methods and schemes within the spirit and scope of the invention as defined by the claims. Further, in order to make the public have a better understanding of the present invention, some specific details are described in detail in the detailed description of the present invention below. The present invention can be fully understood by those skilled in the art without the description of these detailed parts.

[0038] refer to figure 1 , in a preferred embodiment of the present invention, a neural network struc...

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 neural network structure search method applied to picture multi-attribute prediction, which is used for searching the optimal neural network structure in picture multi-attribute prediction problem. The method comprises the following steps: acquiring a picture multi-attribute prediction data set for training the neural network and defining a training target; Greedy searchfor the optimal neural network structure; The parameters of the neural network are retrained and the properties of the new input image samples are predicted. The invention is applicable to the automatic search of the neural network structure of the multi-attribute prediction problem of the real picture, and has better effect and robustness in the face of various complex situations.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a neural network structure search method applied to picture multi-attribute prediction in image processing. Background technique [0002] Image multi-attribute prediction is a topic that researchers in the field of computer vision have been focusing on for a long time. This problem has extensive practical application value in specific applications such as target tracking, target detection, and identity recognition. But again, the problem is quite challenging. One is that there is often a high correlation between its multiple attributes, and the algorithm needs to model the correlation between attributes to improve performance. The second is that while the algorithm models the attribute correlation, it is necessary to reasonably retain the different information of each attribute to improve the discriminative ability of the model. [0003] The current picture attribute ...

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): G06K9/62G06N3/02
CPCG06N3/02G06F18/214
Inventor 黄思羽李玺张仲非
Owner ZHEJIANG UNIV
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