Small sample and zero sample image classification method based on metric learning and meta-learning

Abstract

The invention relates to the field of computer vision recognition and transfer learning, and provides a small sample and zero sample image classification method based on metric learning and meta-learning, which comprises the following steps of: constructing a training data set and a target task data set; selecting a support set and a test set from the training data set; respectively inputting samples of the test set and the support set into a feature extraction network to obtain feature vectors; sequentially inputting the feature vectors of the test set and the support set into a feature attention module and a distance measurement module, calculating the category similarity of the test set sample and the support set sample, and updating the parameters of each module by utilizing a loss function; repeating the above steps until the parameters of the networks of the modules converge, and completing the training of the modules; and enabling the to-be-tested picture and the training picture in the target task data set to sequentially pass through a feature extraction network, a feature attention module and a distance measurement module, and outputting a category label with the highestcategory similarity with the test set to obtain a classification result of the to-be-tested picture.

Description

technical field [0001] The present invention relates to the field of computer vision recognition and transfer learning, and more specifically, to a small-sample and zero-sample image classification method based on metric learning and meta-learning. Background technique [0002] Small-shot and zero-shot image recognition classification has a good application prospect. Among them, small sample image classification can play a huge role in the case where there are only a small number of labeled pictures but a lot of category information. For example, in the target recognition of remote sensing images or infrared images, due to the high cost of airborne radar and remote sensing satellite image acquisition And high difficulty, only a small number of images can be collected as training templates, so the assistance of a small sample recognition system is needed. The zero-shot image classification can play a huge role in the case of no training samples but only category semantic lab...

AI Technical Summary

Problems solved by technology

[0004] However, only one metric is considered in existing research, but in practical applications, different data sets have different data distributions, and only considering one metric may not be applicable to multiple different data sets

In addition, the existing research does not consider that different features have different effects on classification, resulting in features that have no effect on classification, which leads to the introduction of classification noise

Images