Zero-sample image classification method and system based on unknown similar category set

Abstract

The invention discloses a zero-sample image classification method based on an unknown class similar class set, and the method comprises the steps: carrying out the class prediction of an unknown classthrough a class classifier trained through the features of a known class sample, and obtaining the similarity degree of the unknown class and the known class on an image sample feature level; obtaining a similarity relation between the categories from an attribute level by utilizing a relation between the categories of the data set and the attributes; fusing the feature similar category set and the attribute similar category set of the unknown category to generate a similar category set of the unknown category; taking similar known class image samples of unknown classes as training samples toretrain class classifiers of the unknown classes, representing relationships between the classes and attributes by using the distinction degree of the attributes to the classes, and adding feature similarity relationship weights of the unknown classes and the known classes and relationship weights of the unknown classes and the attributes on the basis; and completing category prediction based onthe indirect attribute prediction model. According to the invention, the zero-sample image classification process is more objective and intuitive.

Description

technical field [0001] The invention relates to a zero-sample image classification method and system based on an unknown similar category set, and belongs to the technical field of image processing. Background technique [0002] The zero-sample image classification problem is to establish the connection between known class images and unknown class images through knowledge transfer, so as to realize the requirement that the model trained with known class images can classify images of unknown classes, so as to achieve zero-sample image classification. Sample image classification purposes. [0003] Different from traditional image classification problems, in zero-shot image classification, the image samples to be classified and recognized in the test phase are not involved in the training of the classifier model. In order to achieve knowledge transfer from known classes to unknown classes, using the semantic attributes of images as an intermediary from low-level features to cl...

AI Technical Summary

Problems solved by technology

[0004] However, in the traditional attribute-based zero-shot image classification method, it mainly relies on the category-attribute binary matrix to obtain the correspondence between categories and attributes. This relationship is mainly the most basic relations

Images