A hierarchical semantic embedding model for fine object recognition and implementation method thereof

A fine recognition and hierarchical technology, applied in biological neural network models, character and pattern recognition, instruments, etc., can solve the problem of high cost of additional information labeling, and achieve the effect of reducing complexity

Active Publication Date: 2018-12-28
SUN YAT SEN UNIV
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] In order to overcome the deficiencies in the above-mentioned prior art, the purpose of the present invention is to provide a hierarchical semantic embedding model for fine object recognition and its implementation method, so as to solve the additional problems in the technical solution of fine object recognition that relies on additional information to guide learning. The problem of high cost of information labeling

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
  • A hierarchical semantic embedding model for fine object recognition and implementation method thereof
  • A hierarchical semantic embedding model for fine object recognition and implementation method thereof
  • A hierarchical semantic embedding model for fine object recognition and implementation method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0060] 1. Hierarchical labeling of data

[0061] Taking the image of a bird as an example, it is necessary to prepare hierarchical labeling information other than the image. For example, if the categories of birds are labeled at the four levels of order, family, genus, and species, each piece of training / test data that needs to be provided should include: image, order category label, family category label, genus category label, and species category label .

[0062] 2. Realization of HSE model

[0063] The HSE model includes a backbone network (trunk net) and a branch network (branch net). The role of the backbone network is mainly to extract shallow features from the input image. The role of the branch network has two aspects. One is to further extract deep features from the shallow feature map output by the backbone network, so that the output feature map is suitable for the recognition task of the corresponding level of the branch network; the other is to introduce The k...

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 hierarchical semantic embedding model for fine recognition of an object and an implementation method thereof. The hierarchical semantic embedding model comprises a backbone network, which is used for extracting shallow features of an input image and outputting the features to each branch network in the form of a feature map; several branch networks, which are used for further extracting deep-seated features from the image shallow feature map output by the backbone network, so that the output characteristic map is suitable for the identification task of the corresponding hierarchy of the branch network, by introducing the semantic knowledge embedding mechanism, the invention realizes the guidance of the upper semantic knowledge to the feature learning of the lowerbranch network. The invention solves the problem that the additional information labeling cost is high in the object refinement identification technical scheme which relies on the additional information to guide learning.

Description

technical field [0001] The invention relates to the technical field of object fine recognition, in particular to a hierarchical semantic embedding (Hierarchical Semantic Embedding, HSE) model and a training method thereof for fine object recognition. Background technique [0002] In recent years, the transformation of deep visual computing has ignited the demand for visual understanding and analysis technology in various fields, such as the urgent need for online and accurate retrieval of clothing pictures for e-commerce, the urgent need for accurate matching of vehicles involved in the security industry, and the urgent need for fine identification of wild animals and plants in the agricultural, forestry and environmental protection circles, etc. Wait. These requirements often require the recognition algorithm to be able to distinguish the subordinate categories of a certain basic category in detail, and this technology is usually called the fine recognition of objects. [...

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/231
Inventor 聂琳吴文熙陈添水王青
Owner SUN YAT SEN UNIV
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