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

Zero-sample visual classification method for cross-modal semantic enhancement generative adversarial network

A classification method and cross-modal technology, applied in biological neural network models, neural learning methods, computer components, etc., can solve problems such as easy collapse, deviation, and instability of generated information quality generated models, and achieve easy The effect of classifying and eliminating differences between modalities

Active Publication Date: 2021-10-22
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF11 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the existing technology has the following objective shortcomings: 1. Embedding-based methods measure the similarity between visual information and auxiliary information by learning the embedding space, but because only visible categories of visual information are used to train the embedding space, the generalized zero When learning tasks from samples, this type of method has a bias problem: samples of unseen categories are easily misidentified as visible categories during the training phase.
This type of method is mainly limited by the quality of the generated information and the instability of the generated model. It is often difficult for the generated model to generate fine-grained visual features rich in identification information and semantic information, so that the trained model cannot solve the problem well. Bias problem leads to limited classification performance
In addition, the stability of the generative model is also one of the limitations of this type of method, requiring the generative model to generate finer features will make the generative model more likely to collapse

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 visual classification method for cross-modal semantic enhancement generative adversarial network
  • Zero-sample visual classification method for cross-modal semantic enhancement generative adversarial network
  • Zero-sample visual classification method for cross-modal semantic enhancement generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0062] figure 1 It is a flowchart of a zero-shot visual classification method of a cross-modal semantically enhanced generative adversarial network of the present invention.

[0063] In this example, our model is based on generative adversarial networks (GANs) to solve the task of zero-shot learning by generating data of unseen classes. Traditional methods based on generative confrontation networks or other generative models directly generate visual features extracted by convolutional neural networks (CNN), and they often use the residual neural network (ResNet-101) pre-trained on the ImageNet dataset as the extracted features. architecture. However, such features themselves contain a large amount of label-independent information, so the generated features lack sufficient discrimination and increase the burden on the generation network. In addition, the instability of the generative model leads to poor quality of the generated visual features, and there is still a large gap ...

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 zero-sample visual classification method for a cross-modal semantic enhancement generative adversarial network. The method comprises the following steps: firstly downloading a plurality of sample images and a tag and semantic features corresponding to each sample image, and extracting the visual features of each sample image through a residual neural network; and then constructing and training a cross-modal semantic enhanced generative adversarial network, and training a cross-modal feature classifier based on zero sample classification based on the generative adversarial network, thereby completing visual classification of the to-be-detected image.

Description

technical field [0001] The invention belongs to the technical field of zero-sample learning, and more specifically relates to a zero-sample visual classification method of a cross-modal semantically enhanced generative confrontation network. Background technique [0002] The main goal of zero-shot learning is to train the model with visual information of some visible categories and other auxiliary information (such as text descriptions), so that the learned model can correctly correct the visual information of invisible categories. Classification. Zero-shot learning can be divided into two sub-tasks: Conventional Zero-shot Learning and Generalized Zero-shot Learning. Traditional zero-shot learning only requires the model to complete the classification of invisible categories. Zero-shot learning requires the model to recognize both visible and unseen categories. A typical type of method in the existing methods is based on the embedding space method, which maps auxiliary inf...

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): G06K9/62G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/213G06F18/24Y02D10/00
Inventor 杨阳孙浩天位纪伟徐行
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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