Training method of image recognition model, and image recognition method and device

Abstract

The invention discloses a model training method implemented based on a machine learning technology. The method comprises the steps of obtaining a to-be-trained content sample image and a to-be-trained style sample image; generating a to-be-trained simulation sample image according to the to-be-trained content sample image and the to-be-trained style sample image; obtaining a first prediction scene label and a first prediction style label of the to-be-trained simulation sample image through a to-be-trained image recognition model; obtaining a second prediction scene label and a second prediction style label of the to-be-trained style sample image through the to-be-trained image recognition model; and updating model parameters of the to-be-trained image recognition model according to the prediction label and a labeling label until model training conditions are met, and outputting the image recognition model. The invention further provides an image recognition method and device. According to the invention, more sample images belonging to a target domain are expanded by using the labeled image samples, the collection requirements of different scene data in the target domain are met, and the generalization ability of the image recognition model is improved.

Description

technical field [0001] The present application relates to the technical field of machine learning, and in particular to an image recognition model training method, image recognition method and device. Background technique [0002] The primary task of video understanding and image understanding is to perform scene recognition. Scene recognition is a technology that uses computers to realize human visual functions. Its purpose is to enable computers to process images or videos and automatically recognize scenes in images or videos. . With the development of deep learning, it has become more and more common to use deep learning methods to train image recognition models to solve scene recognition problems. [0003] There are domain problems in scene recognition, that is, the training data of conventional scenes are images in real-life scenes, and some scenes are animation, comics and comics (Animation Comics Games, ACG) types, and the scene features in the new field are sometim...

AI Technical Summary

Problems solved by technology

[0004] However, the ID-CGAN method is too customized, and a single model can only complete the conversion of a specific scene (for example, rain scene). For a specific scene, a large amount of data training is required. If extended to multiple ACG scene, the number of annotations required will be very large, which cannot meet the data collection requirements of various scenes in ACG. Therefore, the trained image recognition model often has poor generalization ability

Images