Neural network training method, target recognition method and related products
A neural network and training method technology, applied in the field of neural network training, can solve problems such as high image quality requirements and unlearned interrelationships, and achieve the effect of high recognition accuracy and rich image samples
Active Publication Date: 2022-01-28
BEIJING SENSETIME TECH DEV CO LTD
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In the prior art, when implementing domain adaptation, the image in the source domain is generally style-transformed to match the target domain, and then the neural network is fine-tuned. The requirements are high, and the fine-tuned neural network only learns the style features of the image in the target domain, and does not learn the relationship between each image in the target domain, as well as the relationship between the target domain and the source domain image
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
[0082] 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.
[0083] 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 present application discloses a neural network training method, a target recognition method, and related products. The training method includes: generating an image in the target domain according to the features extracted by the first neural network from the image samples in the target domain The current pseudo-labeling result of the sample; use the first neural network to process the image sample in the joint domain, and output the processing result of the first neural network; the image sample in the joint domain and its current labeling result include the Image samples in the source domain and their labeling results, image samples in the target domain and their current pseudo-labeling results; according to the processing results of the first neural network, and the current labeling results of the image samples in the joint domain, Adjusting parameter values of network parameters of the first neural network.
Description
technical field [0001] This application relates to the technical field of computer vision, in particular to a neural network training method, a target recognition method and related products. Background technique [0002] In the field of computer vision technology, as the basis of many computer vision applications, the problem of object recognition has always been the focus of research. The domain-adaptive target recognition problem based on the distribution difference between domains has gradually become a research hotspot in the field of computer vision. The research on this problem is of great significance, which is mainly reflected in: if the sample data of the target domain is added during training, the reusability of the classifier or detector can be improved, and the adaptability of the neural network to the new environment can be effectively enhanced, so that The training process of a neural network is largely independent of the application scenario. [0003] In th...
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): G06V30/00G06V10/762G06V10/774G06V10/764G06N3/04
CPCG06V20/00G06V2201/07G06N3/045G06F18/231G06F18/2321G06F18/23213G06F18/214G06F18/24
Inventor 葛艺潇陈大鹏沈岩涛王晓刚李鸿升
Owner BEIJING SENSETIME TECH DEV CO LTD