Zero-sample image classification method based on multi-mode discriminant analysis

Abstract

A zero-sample image classification method based on multi-mode discriminant analysis comprises the steps of constructing matrixes based on the visual feature of training data and semantic features of corresponding categories, getting a mapping matrix, verifying massed learning to get a weight alpha(i), using the mapping matrix to map the visual feature of training data and semantic features of unseen categories to a common space, and classifying test data. According to the invention, a common space between the visual feature of an image and the semantic features of multiple modes can be sought, and higher accuracy is achieved in zero-sample image classification, so the zero-sample image classification method is effective. The method is simple, and has a good effect. Apart from the zero-sample image classification problem, the method can adapt to other multi-mode classification and retrieval problems.

Description

technical field [0001] The invention relates to a method for realizing zero-sample image classification. In particular, it relates to a zero-sample image classification method based on multi-modal discriminant analysis, which establishes the connection between the visual space of the image and the semantic space of the image category through multi-modal discriminant analysis, thereby realizing zero-sample image classification. Background technique [0002] For traditional image classification systems, in order to accurately identify a certain type of image, corresponding labeled training data must be given. However, the labels of training data are often difficult to obtain. Zero-shot image classification is an effective means to solve the problem of missing category labels. Its purpose is to imitate the ability of humans to recognize new categories without seeing actual visual samples. Zero-shot image classification systems use labeled training data, that is, categories tha...

AI Technical Summary

Problems solved by technology

However, the original space formed by the semantic features of category names often cannot describe the category structure of the dataset well.

Images