Domain adaptation method and device, electronic device and storage medium
An adaptation method and domain technology, applied in the field of image recognition, can solve problems such as low domain adaptation efficiency and inability to obtain image data, and achieve the effect of improving semantic segmentation accuracy and efficiency
Pending Publication Date: 2021-04-09
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Sometimes, due to privacy considerations, or data loss and other reasons, the image data of Yuanling cannot be obtained
Therefore, due to the limitation of source domain image data acquisition, domain adaptation efficiency is low, and it is urgent to provide an efficient domain adaptation method
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
[0066] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.
[0067] The terms "first", "second", "third" and "fourth" in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order . Furthermore, the terms "include" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed ste...
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 embodiment of the invention relates to the technical field of artificial intelligence, in particular to a domain adaptation method and device, device and a storage medium. The method comprises the steps of obtaining a to-be-identified image from a target domain; inputting the to-be-identified image into a first segmentation network to obtain a first category proportion, the first segmentation network being obtained by training an image of a source domain; inputting the to-be-identified image into a second segmentation network to obtain a second category proportion and an entropy graph, the entropy graph being a matrix formed by information entropy of each pixel point in the to-be-identified image; and performing domain adaptation on the second segmentation network according to the first category proportion, the second category proportion and the entropy graph. The field adaptation efficiency can be improved.
Description
technical field [0001] The present application relates to the technical field of image recognition, and specifically relates to a field adaptation method, device, electronic equipment, and storage medium. Background technique [0002] Semantic segmentation has become a key step in many modern technology applications. Since the era of deep learning, automatic semantic segmentation methods in various problems have made great progress. However, the semantic segmentation network used for semantic segmentation will suffer a large performance drop in different domains where the samples have different distributions. Therefore, these semantic segmentation networks require pixel-by-pixel annotated images as training samples. Labeling samples is a time-consuming and money-consuming task. [0003] In order to overcome this problem, a domain adaptation method has emerged. Domain adaptation refers to the process of migrating a model trained in a labeled source domain to a target domai...
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 Applications(China)
IPC IPC(8): G06K9/34G06K9/62G06N3/08G06N3/04
CPCG06N3/08G06V10/267G06N3/045G06F18/214
Inventor 刘杰王健宗瞿晓阳
Owner PING AN TECH (SHENZHEN) CO LTD