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

A Triplet network learning method based on a semantic hierarchical structure

A technology of hierarchical structure and network learning, applied in machine learning, image enhancement, instruments, etc., can solve the problems of large network influence, slow convergence of network loss function, and no contribution to triplets in training, and achieves improved performance, enhanced image details, The effect of enhancing separability

Active Publication Date: 2019-06-21
NORTHWESTERN POLYTECHNICAL UNIV
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] But the Triplet network also has many shortcomings: for example, the loss function of the network converges very slowly; the sampling method has a great influence on the network, and whether the network can converge well depends largely on the selected triplet samples Is it reasonable? Moreover, the Triplet network is difficult to train on a large-scale data set. As the number of samples and categories increase, the network will generate a lot of Triplets that do not contribute to the training, and we often need to search the entire space to find the right network training. Really Contributing Hard Triplets
Although these methods showed good results, they did not take hard Triplets into account, so some studies combined the advantages of classification and hard Triplets to improve them. At the same time, in order to make full use of the batch, some studies also proposed to generate hard online in the batch. Triplets

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 Triplet network learning method based on a semantic hierarchical structure
  • A Triplet network learning method based on a semantic hierarchical structure
  • A Triplet network learning method based on a semantic hierarchical structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0044] The invention improves the performance of the Triplet network from a new research direction. Since the similarity between fine-grained sample categories is extremely high, the present invention considers integrating more abstract category information in the semantic level to improve the separability of fine-grained categories. The semantic hierarchy is a concept structure proposed by Quillian and Collins in 1969. In the network structure, various concepts are organized together according to the logical relationship between the upper and lower levels. The higher the level of the concept, the higher the level of abstraction and generalization. Since the traditional N-way softmax ignores the inter-class correlation, and the semantic hierarchy can be used to sort out the intra-class similarity and inter-class difference that exist widely in large-sca...

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 provides a Triplet network learning method based on a semantic hierarchical structure, and the method comprises the steps: constructing the semantic hierarchical structure, carrying outthe hierarchical Triplet sampling, carrying out the hierarchical Triplet network training, and carrying out the enhancement through employing a bilinear feature, thereby updating the parameters of a network. According to the method, the semantic knowledge is used for guiding the hierarchical distinguishing of the sample structure of the network, and the relation between the layers is used for enabling the network to pay more attention to more effective Triplets pairs, so that the effectiveness of samples in the batch is fully mined, and the separability of deep features learnt by the network is improved. Meanwhile, image details are enhanced by utilizing a bilinear function, and the image details and Triplet are jointly trained, so that the performance of the network is further improved.

Description

technical field [0001] The invention relates to the field of machine learning and image feature extraction, in particular to a Triplet network learning method. Background technique [0002] Metric learning is an efficient deep learning method that calculates the error by calculating the similarity between two images to update network parameters. The goal of metric learning is to calculate the similarity between pictures, so that the similarity of heterogeneous pictures is small, and the similarity of similar pictures is large, and finally learn the features with strong separability. From the original Siamese network to the current Triplet network and various improvements and variants of the Triplet network, the method of metric learning reflects its unique superiority. [0003] The Triplet network usually requires input of a triplet, including three samples of anchor, positive, and negative, where positive and anchor are from the same category, and negative and anchor are f...

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): G06N20/00G06T5/00
Inventor 何贵青张琪琦
Owner NORTHWESTERN POLYTECHNICAL 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