Sample expansion method and system based on foreground and background feature fusion
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of sample expansion and feature fusion, applied in the field of remote sensing intelligent recognition
Inactive Publication Date: 2020-10-27
AEROSPACE INFORMATION RES INST CAS
View PDF3 Cites 8 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0008] In order to solve the problem of additional training cost in expanding samples through the data generation network in the prior art, the present invention provides a sample expansion method based on fusion of foreground and background features, including:
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0091] Such as figure 1 As shown, a sample expansion method based on fusion of foreground and background features is characterized in that it includes:
[0092] S1: Divide the remote sensing ground object classification dataset into source data set and target data set based on the ground object category;
[0093] S2: Construct a small-sample source object classification task based on the source data set, and train a feature extractor, a hybrid model and a classifier based on the small-sample source classification task;
[0094] S3: Constructing a small-sample target object classification task based on the target data set;
[0095] S4: performing sample expansion based on the target classification task using the trained feature extractor and the hybrid model;
[0096] Wherein, each task includes: a foreground feature, a background feature and a mixed feature, and the mixed feature is a feature synthesized by using a mixed model of the foreground feature and the background fea...
Embodiment 2
[0130] In order to realize the above method, the present invention also provides a sample expansion system based on fusion of foreground and background features, such as Figure 6 shown, including:
[0131] The division module is used to divide the remote sensing ground object classification data set into a source data set and a target data set based on the ground object category;
[0132] The training module is used to construct a small-sample source classification task based on the source data set, and train a feature extractor, a hybrid model and a classifier based on the small-sample source classification task;
[0133] The classification task module is used to construct a small-sample target feature classification task based on the target data set;
[0134] The sample expansion module is used to perform sample expansion based on the source classification task using the trained feature extractor and the hybrid model;
[0135] Wherein, each task includes: a foreground fea...
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 invention discloses a sample expansion method and system based on foreground and background feature fusion. The method comprises the steps: dividing a remote sensing ground feature classificationdata set into a source data set and a target data set based on ground feature categories; constructing a small sample source ground object classification task based on the source data set, and training a feature extractor, a hybrid model and a classifier based on the small sample source ground object classification task; constructing a small sample target ground object classification task based onthe target data set; performing sample expansion by using the trained feature extractor and the hybrid model based on the target classification task; wherein each task comprises a first task and a second task; the mixed feature is a feature synthesized by a foreground feature and a background feature by using a mixed model; according to the method, the hybrid model is trained based on the classification task, additional manual annotation is not added to expand the training sample, the training cost is reduced, the trained feature extractor and the hybrid model are utilized to expand the target data set, the classifier is trained, and the sample expansion method is realized.
Description
technical field [0001] The invention relates to the field of remote sensing intelligent recognition, in particular to a sample expansion method and system based on fusion of foreground and background features. Background technique [0002] Few-shot learning is to quickly learn a model from a small amount of data. Few-shot image recognition is a challenging emerging field in artificial intelligence. Traditional deep learning methods require a large amount of training data. When the amount of data is relatively small, it is easy to overfit the model and reduce performance. However, there is a shortage of data in many fields, such as the identification of rare species, medical diagnosis pictures, etc. Due to the difficulty in obtaining data or labeling, traditional deep learning techniques cannot be well applied in these fields. [0003] With the development of aerospace technology, my country's earth observation system has been initially formed. We can obtain high-resolutio...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.