Self-adaptive picture classification method in semi-supervised field based on hierarchical relationship

Abstract

The invention relates to a self-adaptive picture classification method in a semi-supervised field based on hierarchical relationship, belongs to the technical field of computer vision processing, and can accurately classify images in a target domain. According to the method, a hierarchical relationship between categories is introduced, and hierarchical relationship information is provided for a prototype by utilizing parent class label and child class label information of all source domains and a small amount of labeled target domain data, so that the prototype distance of the same parent class in a prototype space is relatively short, and a self-adaptive model in the semi-supervised field is helped to obtain a better classification effect. According to the method, the maximum and minimum entropy adversarial learning is carried out on the model by using the gradient inversion layer and using the unsupervised data, so that the prototype vector which has resolution for categories and is not specific to a certain field is extracted, and the classification effect of the model on target domain data is improved. According to the method, the effect on a data set with large domain offset and a large number of categories is ideal, and it is indicated that the method can solve the complex domain offset problem.

Description

technical field [0001] The present invention relates to a semi-supervised field self-adaptive image classification method based on a hierarchical relationship, in particular to a semi-supervised field self-adaptive image classification method based on the hierarchical relationship between subclasses and parent classes, using confrontation ideas and various loss functions The classification method belongs to the technical field of computer vision processing. Background technique [0002] In recent years, deep learning networks have achieved great success in image classification tasks, but the training of deep networks requires a large amount of manually labeled data. However, it is very time-consuming and energy-consuming to manually label all collected data in practical application scenarios. , and even some data annotations for special problems can only be done by experts in related fields. [0003] In order to better deal with unlabeled or only a small number of labeled d...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies in the prior art, in order to solve the technical problem of the lack of sample category hierarchical relationship in the existing minimum maximum entropy semi-supervised domain adaptive method, a semi-supervised domain adaptive method based on hierarchical relationship is proposed Image Classification Method

Images