Zero sample image classification method and system based on a convolutional neural network and a factor space

Abstract

The invention provides a zero sample image classification method and system based on a convolutional neural network and a factor space, and the method comprises the steps: building a unified zero-sample classification neural network: firstly, extracting image features in a data set through a classical convolutional neural network, and enabling the image features to serve as the input of the neuralnetwork; the dimensionality of known factors is reduced by using a factor pressure reduction technology, and the known factors and potential factors are embedded into a network to serve as an intermediate layer to jointly determine a final classification result; the network enables image input to final category output. And training a zero sample classification network, and iteratively determiningnetwork model parameters. And identifying the image by using the zero sample classification neural network to finish classification of the zero sample image. According to the method, a convolutionalneural network model is used for uniformly processing the relationship among the visual space, the factor space and the category space, the problem that the generalization ability of specific linear or nonlinear function expression is not high is solved, and the factors serving as auxiliary knowledge are embedded into the network and are easy to understand, train and use.

Description

technical field [0001] The invention relates to a zero-sample image classification method and system based on a convolutional neural network and a factor space, and belongs to the technical field of image recognition. Background technique [0002] Backed by large-scale available datasets, object recognition algorithms in computer vision have made breakthrough progress in recent years. However, manually collecting and labeling data is a very time-consuming and labor-intensive work, especially for the classification of images of some rare objects or similar objects, experts are required to distinguish different categories. In the absence of training data, it is difficult for general methods to perform correct recognition. The visual recognition problem at this time is usually called zero-shot classification or zero-shot learning. [0003] In the zero-sample classification problem, the training set is full of image data labeled with class labels (also called visible classes), ...

AI Technical Summary

Problems solved by technology

Existing technologies usually express these models by assuming specific linear or nonlinear functions. This specific linear or nonlinear function has limited expression ability and weak generalization ability. For different zero-sample classification problems, researchers need to try to use different linear or nonlinear functions

Images