A kind of image grading granularity migration method, system, device and medium
An image and granular technology, applied in character and pattern recognition, instruments, computing, etc., can solve problems such as hindering knowledge transfer and granularity differences
Active Publication Date: 2022-07-29
UNIV OF SCI & TECH OF CHINA +1
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] There are serious granularity differences in the existing visual recognition tasks, that is, the two granularities need to correspond to different visual expression distributions, thus hindering the transfer of knowledge
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
[0042] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. It should be understood, however, that these descriptions are exemplary only, and are not intended to limit the scope of the present invention. In the following detailed description, for convenience of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, that one or more embodiments may be practiced without these specific details. Also, in the following description, descriptions of well-known structures and techniques are omitted to avoid unnecessarily obscuring the concepts of the present invention.
[0043] At present, the categories of objects usually form hierarchical trees of different granularities, for example, many different species of albatrosses make up the albatross family. In the past few years, most researches have focused on ...
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 present invention provides an image classification granularity migration method, system, device and medium. The method includes: acquiring visual features, parent-category semantic descriptions and sub-category semantic descriptions of images; first matching the visual features with the parent-category semantic descriptions by using a double-semantic retention network, and predicting an image through the first matching The parent category of the image; determine the scope of the subcategory of the image by the parent category of the image; obtain the visual features of the preset area in the visual features, and use the double semantic retention network to combine the visual features of the preset area with the semantics of the subcategory. Describes performing a second match within the scope of the sub-category by which the sub-category of the image is predicted. It is realized that only the image annotation of the parent category and the category description of the hierarchical granularity are used to solve the identification problem of the corresponding sub-category.
Description
technical field [0001] The invention relates to the field of artificial intelligence, in particular to a method, system, device and medium for image classification granularity migration. Background technique [0002] The categories of objects usually form a hierarchical granularity tree. For example, birds have three different classifications: "class", "family", and "species". Currently, most researchers focus on addressing specific granularity categories in visual recognition, such as the "family" category (parent category) or its subordinate "species" category (subcategory). Compared to parent categories, subcategories usually provide more valuable information, but the annotation of their data is also more difficult to obtain. [0003] The existing visual recognition tasks have serious granularity differences, that is, the two granularities need to correspond to different visual expression distributions, thus hindering the transfer of knowledge. [0004] Therefore, how ...
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): G06V10/764G06V10/774G06V10/82G06K9/62
CPCG06F18/24G06F18/214
Inventor 张勇东闵少波谢洪涛
Owner UNIV OF SCI & TECH OF CHINA