Domain self-adaptive method and device based on comparative adversarial learning

An adaptive, field-based technology, applied in neural learning methods, instruments, biological neural network models, etc.

Pending Publication Date: 2022-02-18
BEIJING UNIV OF TECH
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such methods require

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
  • Domain self-adaptive method and device based on comparative adversarial learning
  • Domain self-adaptive method and device based on comparative adversarial learning
  • Domain self-adaptive method and device based on comparative adversarial learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Such as Figure 5 As shown, this method of domain adaptation based on contrastive adversarial learning, the method includes the following steps:

[0039] (1) Use the loss function L on the source domain data cls (x s ,y s ) to train the entire network model, the optimization process is defined as formula (1):

[0040]

[0041] Among them, L ce ( , ) is the cross-entropy loss, θ g , θ c1 θ c2 Respectively, the feature network G, C 1 , C 2 parameters in

[0042] (2) Fix the parameters in the feature extractor and only update the classifier C 1 and C 2 , minimize the classification loss of the classifier and maximize the discriminative difference between the classifier and the sample in the target domain. The loss function is formula (2):

[0043]

[0044] Among them, L dis ( , ) means that the dual classifier only updates the parameters in the classifier for the discriminative difference of the target domain samples, and at the same time, the model adds...

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

A domain self-adaptive method and device based on comparative adversarial learning are provided. On source domain data, a loss function Lcls(xs, ys) is used for training a whole network model, parameters in a feature extractor are fixed, only classifiers C1 and C2 are updated, classification loss of the classifiers is minimized, target domain sample discrimination differences of the classifiers are maximized, the parameters in the classifiers C1 and C2 are fixed, Ldis is used for updating parameters in the feature extractor, and a self-adaptive loss item is reserved in the step. The classifier C1 and the classifier C2 respectively use features of different data enhancement modes, so that diversity of the classifiers is guaranteed, the double classifiers can more efficiently find samples at classification boundaries, features learned by the model contain more effective information, so that the problem of self-adaption in the unsupervised field is well solved. On the basis of a traditional double-classifier-based confrontation method, the disclosed method takes decision boundaries of classifiers on a target domain into account and also pays close attention to inter-domain differences.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a field adaptive method based on contrastive confrontation learning and a field adaptive device based on contrastive confrontation learning. Background technique [0002] The invention focuses on solving the image classification problem of unsupervised domain self-adaptation, and combines the deep network and domain self-adaptive problems. By processing the characteristics of the samples in the feature space, the difference between the distribution of the source domain and the target domain is reduced, so that the knowledge learned in the source domain can also be applied to the target domain. Deep unsupervised domain adaptation is a research field that has attracted much attention, and a large number of scholars have participated in the research work in this field. At present, deep unsupervised domain adaptation methods can be mainly divided into three categorie...

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
CPCG06N3/08G06F18/22G06F18/241
Inventor 孙艳丰陈亮王少帆
Owner BEIJING UNIV OF TECH
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