Zero sample classification method and device based on semantic enhancement of encyclopedic knowledge

Abstract

The invention relates to the fields of pattern recognition, machine learning and computer vision, and provides a zero sample classification method based on semantic enhancement of encyclopedic knowledge, which aims to solve the problem that the existing zero sample image classification method cannot give consideration to both word vector language information range and processing efficiency. The zero sample classification method comprises the steps of: S1, classifying unknown-class images by means of a trained convolutional neural network classifier, and subjecting semantic features of classification result tags to convex combination to serve as semantic features of the unknown-class images; S2, and classifying the semantic features of the unknown-class images obtained in the step S1 and semantic features in a pre-constructed semantic feature space by means of a nearest neighbor classifier, so as to obtain final classes of the unknown-class images. The zero sample classification method and a zero sample classification device provided by the invention enhance the global information of word vectors, so as to improve the accuracy of image zero sample classification.

Description

technical field [0001] The invention relates to the fields of pattern recognition, machine learning, and computer vision, and in particular to a zero-sample classification method and device based on semantic enhancement of encyclopedia knowledge. Background technique [0002] With the development of deep learning technology and the rapid improvement of computer computing power, the fields of artificial intelligence and computer vision are developing rapidly. As the most basic task among them, the performance of image classification methods has also been greatly improved. The image classification task requires the computer to distinguish the category of objects in a picture based on the prior knowledge learned on the training data set. Traditional image classification tasks require a large number of training images labeled with object categories. Collecting labeled training images is time-consuming and expensive. Zero-sample image classification hopes to help the computer ...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that the existing zero-shot image classification method cannot take into account the range of word vector language information and processing efficiency, one aspect of the present invention proposes a zero-shot image classification method based on encyclopedia knowledge semantic enhancement The sample classification method includes the following steps:

Images