Development method and system of small sample classification model based on graph convolutional neural network

Abstract

The invention belongs to the field of computer vision, particularly relates to a development method and system of a small sample classification model based on a graph convolutional neural network, andaims to solve the problems that an existing model is poor in performance and needs a large number of training samples with labels when applied to a new task. The method comprises the steps of extracting a knowledge graph formed by an undirected graph, and obtaining knowledge information related to a task; extracting experience information of the original model in the training process of the old task; fusing the knowledge information and the empirical information to form a new fusion graph; and obtaining a new task-oriented cognitive developed classification model by establishing a relationship between a new task category and an old task category and carrying out model training. According to the method, in the task migration process, a new task can achieve rapid and accurate visual migration without providing a large number of samples with labels, the utilization rate of the model is greatly increased, the cost of training the model is reduced, and the time of training the model is shortened.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a method and system for developing a small-sample classification model based on a graph convolutional neural network. Background technique [0002] With the continuous development of related technologies in the field of computer vision, the application range of computer vision technology is becoming more and more extensive. While the visual algorithm is gradually maturing, the model's dependence on large-scale image samples has become an unavoidable problem in model training. For fields where sample collection is difficult, even in fields that do not have large-scale samples, the collection of labeled samples has become a difficult problem that restricts the development of computer vision technology. Due to the continuous expansion of the field of human cognition, new task categories are gradually discovered. However, the test task objects of most target recognition m...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, that is, the performance of existing models is poor when applied to new tasks and a large number of labeled training samples are required, the present invention provides a small-sample classification model based on graph convolutional neural network. A developmental approach that includes:

Images