Zero-sample image classification method and device based on double auto-encoders

A sample image and self-encoder technology, applied in the field of image classification, can solve the problem of the semantic gap between unresolved low-level visual features and high-level semantic features, and achieve the effect of alleviating the semantic gap problem and enhancing the generalization ability

Active Publication Date: 2021-07-13
CHONGQING UNIV OF POSTS & TELECOMM
View PDF11 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this patent directly learns the visual-semantic projection from visual features to semantic features

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 image classification method and device based on double auto-encoders
  • Zero-sample image classification method and device based on double auto-encoders
  • Zero-sample image classification method and device based on double auto-encoders

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0071] Such as figure 1 as shown, figure 1 A schematic diagram of the overall flow of a zero-shot image classification method based on a dual autoencoder provided in this embodiment, specifically including the following steps:

[0072] Taking the AWA2 dataset as an example, the specific implementation process is described in detail. The AWA2 data set contains 50 animal categories, of which 40 categories are used as visible categories for training models, and 10 categories are used as unseen categories for testing. Each category (including visible and unseen categories) consists of 85-dimensional semantic attributes express.

[0073] Specifically, suppose Ω s = {X, S, Y} and Ω u ={X u , S u , Y u} denote N samples from C visible classes and c u N of unseen classes u samples. where X∈R d×N , represent the d-dimensional image visual features of samples of seen and unseen classes, respectively, and the corresponding labels are Y∈R c×N with S∈R k×N with refer to th...

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 image classification method and device based on double auto-encoders, and relates to the technical field of image classification, visual and semantic features are projected to a public space to learn potential semantics, and a consistent weight matrix is constructed based on graph knowledge to enable double projections to keep a consistent data structure. An epsilon-traction technology is introduced, a visible class classifier based on label relaxation is designed, the discrimination of potential language meaning and the generalization ability of a model are enhanced, and the method comprises the following steps: acquiring a sample image; constructing a visual feature vector, then establishing visual and semantic feature spaces and constructing a consistency weight matrix, constructing a regularization self-encoder based on double graph embedding, introducing an epsilon-traction technology, and establishing a visible class potential semantic classifier based on label relaxation, training a double discrimination graph regularization self-encoding model to obtain a zero sample classification model, and obtaining class labels of unseen class test samples in a public space by using a distance calculation formula.

Description

technical field [0001] The invention relates to the technical field of image classification, in particular to a zero-sample image classification method and device based on a double autoencoder. Background technique [0002] Zero-shot classification is an important research direction in image classification and belongs to an important branch of transfer learning. Although researchers have proposed some solutions, the technology still faces many challenges. Among them are the semantic gap between the low-level visual features and the high-level semantics, and the lack of discrimination of semantic attributes. [0003] In recent years, image classification based on deep learning has made breakthrough progress, but collecting and labeling training images is a very time-consuming and laborious work. Therefore, some researchers proposed the concept of "zero-shot learning", that is, to identify unseen classes with missing labels by transferring the known class knowledge of labels....

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): G06K9/62G06N3/08
CPCG06N3/08G06F18/24143
Inventor 米建勋台德宝陈涛向菲钱基业江金洋
Owner CHONGQING UNIV OF POSTS & TELECOMM
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