Unlock instant, AI-driven research and patent intelligence for your innovation.

A zero-shot image classification method based on meta-learning adversarial networks

A sample image and classification method technology, applied in neural learning methods, biological neural network models, computer components, etc., can solve problems such as easy distortion of visual features, achieve outstanding classification ability, alleviate domain offset problems, and improve performance Effect

Active Publication Date: 2022-07-08
TIANJIN UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the introduction of the variational lower bound of VAE, the generated visual features are easy to be distorted.

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 zero-shot image classification method based on meta-learning adversarial networks
  • A zero-shot image classification method based on meta-learning adversarial networks
  • A zero-shot image classification method based on meta-learning adversarial networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] Certain terms are used in the specification and claims to refer to particular components. It should be understood by those skilled in the art that hardware manufacturers may refer to the same component by different nouns. The description and claims do not use the difference in name as a way to distinguish components, but use the difference in function of the components as a criterion for distinguishing. As mentioned in the entire specification and claims, "comprising" is an open-ended term, so it should be interpreted as "including but not limited to". "Approximately" means that within an acceptable error range, those skilled in the art can solve technical problems within a certain error range, and basically achieve technical effects.

[0064] Furthermore, the terms "first," "second," etc. are used for descriptive purposes only and should not be construed to indicate or imply relative importance.

[0065] In the invention, unless otherwise expressly specified and limi...

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 belongs to the technical field of image classification, and in particular relates to a zero-sample image classification method based on a meta-learning confrontation network. The training method of meta-learning is used in the zero-sample classification task. , in the training phase, the learning task of zero-sample image classification is simulated, which not only completes the generation process of visual features, but also ensures the alignment relationship of different classifiers. Under the supervision of the visual classifier, the classifier is better trained, so as to synthesize visual features and semantic features that are closer to the real distribution, and design a zero-sample image classification technology suitable for real situations. The invention can make the generalized zero-sample image classification ability more prominent, improve the generalization ability of the model, and alleviate the common field offset problem in zero-sample learning.

Description

technical field [0001] The invention belongs to the technical field of image classification, and in particular relates to a zero-sample image classification method based on a meta-learning confrontation network. Background technique [0002] In recent years, machine learning has been widely used in natural language processing, computer vision, speech recognition and other fields, and in the field of computer vision, image classification task is one of the most concerned and widely used tasks, and various classification technologies emerge in an endless stream , the performance continues to improve. In machine learning tasks, the supervised learning method that achieves classification through a large number of manually annotated images is the traditional method of image classification and has been well applied in real life. However, it is not easy to collect enough samples for each class of images and label them in practice, which consumes a lot of labor. It is not difficul...

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 Patents(China)
IPC IPC(8): G06V10/764G06K9/62G06N3/04G06N3/08G06V10/774
CPCG06N3/08G06N3/045G06F18/2415G06F18/214
Inventor 冀中崔碧莹
Owner TIANJIN UNIV