A Method of Improving Model Domain Adaptability Based on Markov Open Composite Domain
An adaptive, composite domain technology, applied in the field of computer vision, can solve the problems of inability to guarantee the distribution of individuals in the domain, sufficient adequacy, loss of data information, etc., and achieve good domain adaptation effect and sufficient extraction effect.
Active Publication Date: 2021-11-02
BEIJING UNIV OF CIVIL ENG & ARCHITECTURE
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] In composite domains, there is no guarantee that the distribution among individuals in the domain is sufficient;
[0008] The constructed encoder sets all the data information less than 0 to 0, so that the data information less than 0 is lost
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0060] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.
[0061] Those skilled in the art will understand that unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the word "comprising" used in the description of the present invention refers to the presence of said features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components, and / or groups thereof. It will be understoo...
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
Login to View More Abstract
The present invention provides a method for improving the adaptability of the model domain based on the Markov open composite domain, which proposes the concept of the Markov open composite domain, and mixes different data sets through the Markov process to ensure the composite domain The distribution of elements from different datasets is more dispersed in , so as to achieve better domain adaptation effect. The method provided by the present invention also has the following beneficial effects: by using the Markov process combined with Bernoulli's Theorem of Large Numbers, multiple domains without domain labels are mixed into a Markov compound domain, and then combined with an open domain to form a Markov composite domain. Open the composite domain to ensure that the distribution of elements from different data sets in the composite domain is more dispersed, so as to achieve better domain adaptation effect; at the same time, construct a neural network encoder based on parametric corrected linear unit, so that the neural network can encode In the process, all data information can be fully utilized, so as to achieve the purpose of fully extracting image features.
Description
technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for improving model domain adaptability based on Markov open composite domains. Background technique [0002] Image recognition is a technology that uses computers to process, analyze and understand images, and to identify targets and objects in different patterns. It has a very important influence and role in the process of intelligent data collection and processing with images as the main body. There is no essential difference between computer image recognition technology and human image recognition in principle, but the machine lacks the influence of humans on sensory and visual differences. When human beings see a picture, our brain will quickly sense whether we have seen this picture or a picture similar to it, and our brain will identify it according to the categories that have been classified in the stored memory to see if there is something similar to the...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06K9/46
CPCG06V10/457G06F18/2415G06F18/214
Inventor 谭志刘兴业
Owner BEIJING UNIV OF CIVIL ENG & ARCHITECTURE