Reward determination method for an image description model l and electronic equipment
A technology for image description and determination method, applied in still image data retrieval, metadata still image retrieval, data processing applications, etc., can solve the problem of low accuracy of image description, solve the problem of uneven word distribution, and improve accuracy sexual effect
Active Publication Date: 2019-08-16
暗物智能科技(广州)有限公司
View PDF6 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] In view of this, an embodiment of the present invention provides a method for determining rewards for an image description model and an electronic device to solve the problem of low accuracy of image description
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
[0076] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.
[0077] In order to clearly describe the embodiments of the present invention, some nouns involved in the embodiments of the present invention are explained as follows:
[0078] (1) Training set: a collection of several images, each image corresponds to a certain number of label descriptions; for example, each image in the training set corresponds to 5 la...
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 relates to the technical field of image description, in particular to a reward determination method for an image description model and electronic equipment, and the reward determinationmethod comprises the steps: obtaining a label description of a test image and a generation description of a preset image description model based on the test image; based on the test image and the generation description thereof, determining the correlation between the test image and the generation description; extracting a global most similar image of the test image in a training set; calculating acorrelation difference value of the test image relative to the global most similar image and the generation description so as to determine a first global reward; and updating the reward of each wordin the generation description based on the first global reward and the reward of the n-tuple. The first global reward obtained through calculation represents the constraint item of global discrimination, and the constraint item enables the description between the test image and the global most similar image to have distinction and discrimination, thereby improving the accuracy of image description.
Description
technical field [0001] The invention relates to the technical field of image description, in particular to a method for determining rewards for an image description model and electronic equipment. Background technique [0002] The task of image description is a common task in everyday life. Its purpose is to generate a grammatical natural language description describing the content of the image based on the content of the image. This task can be applied in early childhood education, navigation and guidance in real life. [0003] The intersection of computer vision and natural language processing is the two major fields of artificial intelligence. Although both fields use similar artificial intelligence and machine learning methods for field research, there is still little interaction between the two fields. In recent years, however, the fields of natural language processing and computer vision have made enormous strides in analyzing and generating text and understanding im...
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): G06K9/62G06F16/58G06Q30/02
CPCG06F16/58G06Q30/0217G06F18/214
Inventor 陈添水吴捷梁小丹林倞
Owner 暗物智能科技(广州)有限公司