Neural network training and classification method and device, equipment and storage medium
A neural network training and neural network technology, applied in the field of neural network training and classification methods, devices, equipment and storage media, can solve the problems of large field span and poor model performance improvement effect.
Pending Publication Date: 2022-01-11
SHANGHAI SENSETIME INTELLIGENT TECH CO LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, due to the large domain span between the upstream task corresponding to the computer vision dataset and the downstream task corresponding to the current application scenario, the performance improvement effect of the model is not good.
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
[0063] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only It is a part of the embodiments of the present disclosure, but not all of them. The components of the disclosed embodiments generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the present disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those ski...
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 provides a neural network training and classification method and device, equipment and a storage medium, and the method comprises the steps: obtaining each training picture sample and text description content corresponding to each training picture sample; extracting picture feature information from the training picture sample, and extracting text feature information from the text description content corresponding to the training picture sample; determining a loss function value of the neural network to be trained based on the extracted picture feature information and text feature information; and under the condition that the iterative training cut-off condition of the neural network is not met, adjusting the network parameter value of the neural network based on the determined loss function value, and training the adjusted neural network again until the iterative training cut-off condition of the neural network is met, thereby obtaining the trained neural network for processing the target picture. According to the invention, the text feature information is utilized to provide additional supervision signals for picture training, and the performance of network training is greatly improved.
Description
technical field [0001] The present disclosure relates to the technical field of machine learning, in particular, to a neural network training and classification method, device, equipment and storage medium. Background technique [0002] With the continuous development of deep learning, various machine learning models have achieved more and more success in various industries, and can be widely used in various application scenarios such as image classification and target detection. [0003] In practical application scenarios, there may be a small number of training samples that can be used, and the performance of directly training a neural network model on a small number of training samples often leads to poor performance. In order to solve this problem, in related technologies, a large computer vision data set can be used to pre-train a feature extractor, and then the feature extractor is migrated to a specific application scenario and then the neural network model is trained...
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 IPC IPC(8): G06V10/774G06V10/764G06V10/74G06V10/82G06V10/40G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F18/22G06F18/214G06F18/24
Inventor 黄俊钦高梦雅王宇杰
Owner SHANGHAI SENSETIME INTELLIGENT TECH CO LTD