Image classification method and system based on small sample learning, storage medium and terminal

Abstract

The invention discloses an image classification method and system based on small sample learning, a storage medium and a terminal. The method comprises the steps of determining a to-be-classified image data set; extracting a plurality of types of image data samples in the image data set, and establishing an image support set based on the plurality of types of image data samples; extracting a plurality of types of second image data samples from the remaining image data samples after extraction in the image data set to construct a query set; and performing generalization processing on a pre-trained small sample classification network according to the image support set, inputting each image data sample in the image query set into the generalized small sample classification network, and outputting the category of each image data sample. Therefore, by adopting the embodiment of the invention, the feature fusion processing is carried out by extracting the sample features of the support set and the query set, so that the two sets mutually enhance the related features between the samples to highlight the features interested between the samples, and the image classification precision is improved.

Description

technical field [0001] The invention relates to the field of computer deep learning technology, in particular to an image classification method, system, storage medium and terminal based on small sample learning. Background technique [0002] With the development of deep learning, people have proposed an image classification method based on deep neural network, which needs to be trained through a large number of samples, so that the deep neural network has better performance. However, in some practical applications, such as object tracking or object detection, we may only have limited samples, making it difficult to build a large set of valuable, labeled samples. Therefore, small sample learning is an application of meta-learning in the field of supervised learning. By constructing different meta-tasks to solve the m-way k-shot problem, it is suitable for improving the generalization ability of the classification model in the case of a small number of samples. [0003] Exis...

AI Technical Summary

Problems solved by technology

The problems of metric-based learning methods are as follows: These methods embed the samples of the support set and query set into the feature space, but do not make full use of these extracted sample features, which will reduce the generalization ability of the classification model

Images