Zero sample classification method based on extreme learning machine

Abstract

The invention discloses a zero sample classification method based on an extreme learning machine, and the method is used for image classification. The method comprises the following steps: extracting the visual features of a training image at a training state, and extracting the training semantic features corresponding to the visual features of the training image; randomly generating a first input weight and a first threshold value for L junctions, and calculating a first output matrix of a hidden layer through employing a hidden layer mapping function; calculating the output weight of a network through the training semantic features and the first output matrix of the hidden layer; extracting the visual features of a test sample at a test stage, randomly generating a second input weight and a second threshold value for L junctions, and calculating a second output matrix of the hidden layer through employing the hidden layer mapping function; calculating an embedded vector, correspondingly located in a semantic space, of the second output matrix through the output weight, and judging the type of the test sample according to the similarity of the embedded vector with the semantic features in a semantic feature space. The method reduces the training time, and improves the classification speed of the image.

Description

technical field [0001] The invention relates to an image classification method in the field of machine learning, in particular to a zero-sample classification method based on an extreme learning machine. This method is aimed at the long training time in a single hidden layer feedforward neural network and cannot guarantee an optimal solution , poor generalization ability, easy over-fitting and other shortcomings, using a simple and effective extreme learning machine for classification can significantly improve the classification efficiency of images. Background technique [0002] With the needs of practical applications, zero-shot classification has received a lot of attention. The traditional classification problem is to use the training data set to learn a classifier, and then use the learned classifier to classify the test samples, where the test samples belong to the categories in the training data set, and the zero-sample classification can classify the classifiers that...

AI Technical Summary

Problems solved by technology

The advantage of the nonlinear model is that it can fit the mapping relationship between modes well, and can provide an effective model for a large number of natural or artificial phenomena that are difficult to handle with traditional classification techniques, but the training time is too long and the efficiency is low

Images