Image semantic understanding method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses an image semantic understanding method and device, equipment and a storage medium. The method comprises the steps that target image information is acquired; the target image information is input into a pre-trained semantic understanding model, a semantic classification result output by the semantic understanding model is obtained, and the semantic understanding model is obtained through training based on associated image information and text information; and determining a semantic understanding result according to the semantic classification result. According to the method provided by the embodiment of the invention, the target image information is classified through the semantic understanding model obtained by training directly based on the obtained associated image information and text information, so that the annotation amount during model training is simplified, and the semantic understanding model with accurate classification can be obtained by training with less annotation.

Description

technical field [0001] The embodiments of the present invention relate to the field of computer technology, and in particular to an image semantic understanding method, device, equipment and storage medium. Background technique [0002] Image semantic understanding is a very valuable direction. Many scenarios need to use image semantic information, such as image labeling, information recommendation using images as input, etc. In order to understand the semantic information of the image, the usual method is to label the image, for example, the style of the image is "fashion trend", and the image describes "damaged goods", and then use the image data labeled with text information to train the image semantic understanding model , understand the semantics of product images. [0003] In the process of realizing the present invention, the inventors found that there are at least the following technical problems in the prior art: in order to be able to train an accurate semantic un...

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the present invention, the inventor found that there are at least the following technical problems in the prior art: in order to be able to train an accurate semantic understanding model, a large amount of annotation is required, and the annotation complexity is very high

When the amount of annotation is insufficient and the annotation is unreasonable, the accuracy of the trained semantic understanding model is low

Images