Zero sample classification method based on dual-triple deep metric learning network

A technology of metric learning and classification methods, which is applied in the field of zero-sample classification based on the double-triple deep metric learning network, can solve the problem of not making full use of the differences and connections between visual features and semantic features of samples, and achieve simple structure implementation and training The effect of simple method and few training parameters

Active Publication Date: 2019-08-16
TIANJIN UNIV
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such methods do not make full use of the difference and con

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
  • Zero sample classification method based on dual-triple deep metric learning network
  • Zero sample classification method based on dual-triple deep metric learning network
  • Zero sample classification method based on dual-triple deep metric learning network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] A zero-shot classification method based on a double-triple deep metric learning network of the present invention will be described in detail below with reference to the embodiments and drawings.

[0027] Such as figure 1 As shown, a zero-sample classification method based on a double-triple deep metric learning network of the present invention, first, utilizes a convolutional neural network to extract visual features of sample images; utilizes manually labeled attribute features as sample semantic features, and the method includes Training phase and testing phase: In the training phase, firstly, the semantic features of the training samples are input to the mapping network, and the output of the mapping network is sent to the visual space; in the visual space, a pair of training sample semantic features and training sample visual features belonging to the same category are selected to form Positive sample pair, and then select a training sample semantic feature of a dif...

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 relates to a zero sample classification method based on a double-triple deep metric learning network, which comprises the following steps of: inputting semantic features of samples intoa mapping network, and outputting the semantic features to a visual space; in a visual space, selecting a pair of semantic features and visual features belonging to the same category to form a positive sample pair, then selecting a semantic feature different from the positive sample pair to form a triple, and inputting the triple into a semantic-guided triple network; selecting a pair of semanticfeatures and visual features belonging to the same category are selected to form a positive sample pair, then a visual feature different from the positive sample pair in category to form a triple, andinputting the triple into a visual guidance triple network; inputting the output of the semantic-guided triple network and the output of the visual-guided triple network into a double-triple loss function for calculation; and finally, classifying the test samples by using a nearest neighbor classifier. The structure is easy to realize, the training method is simpler, the training parameters are fewer, and training can still be carried out under the condition that computer hardware equipment is poorer.

Description

technical field [0001] The invention relates to a zero-sample classification method. In particular, it concerns a zero-shot classification method based on a dual triplet deep metric learning network. Background technique [0002] In recent years, deep learning has been vigorously developed because of its outstanding performance on large-scale dataset classification tasks. However, a prominent problem is becoming more and more obvious. It takes a lot of manpower and material resources to obtain labeled data, and in some cases it is even extremely difficult to obtain, such as images of endangered animals. Compared with deep learning that requires a large amount of labeled data, humans only need a small number of samples, or even no samples to perform recognition tasks. For example, when a person already knows a cat and tells him that a tiger has a "king" pattern on its forehead, he is very likely to recognize the tiger. Inspired by this ability of human beings, scholars beg...

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): G06K9/62
CPCG06F18/24147G06F18/214
Inventor 冀中汪海庞彦伟
Owner TIANJIN 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