Unsupervised two-stage field adaptive method

An adaptive and unsupervised technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as reducing the distribution difference between domains, achieve high classification accuracy, improve performance, and achieve the effect of effective knowledge transfer

Pending Publication Date: 2022-05-27
CHONGQING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims at the problem of insufficient reduction of inter-domain distribution differences caused by learning a projection subspace in the current domain adaptive method based on low-rank subspace learning, and proposes a two-stage pseudo-label accurate domain adaptive method, using categories that are meaningful for classification Prior information and local structure information, explore the inherent laws hidden in the bottom layer of the data, and improve the robustness, generalization and efficiency of the cross-domain image classification model

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
  • Unsupervised two-stage field adaptive method
  • Unsupervised two-stage field adaptive method
  • Unsupervised two-stage field adaptive method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0010] The present invention proposes an unsupervised two-stage domain adaptive method, which realizes the alignment between the source domain and the target domain on four levels, and reduces distribution differences. They are: subspace alignment, data alignment, label alignment, and graph structure alignment.

[0011] Subspace Alignment Item: P s and P t Defined as the source domain subspace projection and the target domain subspace projection respectively, minimizing the distance between the projections of two specific domains in the manifold space can reduce the domain shift. The subspace alignment term is defined as follows:

[0012]

[0013] Data alignment term: In order to narrow the distribution difference between the source domain and the target domain, an optimal target projection P is learned by using the intrinsic information of the data t . The target data is assumed to be linearly represented by the source domain data in a common subspace, and by imposing ...

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 an unsupervised two-stage field adaptive method. According to the method, the accuracy of the pseudo-label is enhanced by using the continuously updated target domain projection subspace, the precise pseudo-label is fed back to the target domain projection subspace, and the two stages are alternately updated, so that a discrimination subspace with optimal classification performance can be obtained. Specifically, in the first stage, two projection subspaces are used for mapping data of a source domain and a target domain into corresponding low-dimensional subspaces, and meanwhile, a feature alignment loss function based on MMD is used for clustering samples of the same category from a cross-domain category space, so that conditional distribution differences are further reduced; and a graph regular term is constructed in a target domain projection subspace according to semantic information (the source domain is label information and the target domain is pseudo label information) of all samples and distance information between two sample points, and adjacent information of original data is kept. And in the second stage, training an SVM classifier by using the subspace projection obtained in the first stage, calculating a pseudo label of a target domain sample, and feeding back the precise pseudo label to the first stage. The method has the advantages that geometric structure information and prior label information in the knowledge migration process are considered, and the accuracy of image classification can be effectively improved.

Description

technical field [0001] An Unsupervised Two-Stage Domain Adaptation Method. Background technique [0002] Image classification based on traditional machine learning assumes that the test samples and training samples need to satisfy independent and identical distribution, and at the same time, a large number of labeled samples with the same distribution as the test data are required to ensure the generalization performance of the model. These two conditions are difficult to achieve in real applications. Domain adaptation can break through the implicit assumptions of traditional machine learning. It is expected to use labeled source domain data and unlabeled target domain data to build a cross-domain learning model, which can solve the problem of scarcity of training sample labels and the difficulty of truly satisfying independent and identical distribution in machine learning. A question of conditions. Contents of the invention [0003] The present invention aims at the pro...

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): G06K9/62G06N3/08G06V10/764
CPCG06N3/088G06F18/2155
Inventor 陶洋杨娜田家旺王一强
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