A self-learning small sample remote sensing image classification method based on consistency constraint

Abstract

The invention relates to a consistency constraint-based self-learning small sample remote sensing image classification method, which is characterized in that a self-learning method is embedded into adeep convolutional neural network, a self-learning small sample remote sensing image classification method is provided, and the advantages of the self-learning method and the deep convolutional neuralnetwork are comprehensively utilized. In the iterative training process, a consistency discrimination criterion is adopted to continuously generate pseudo label samples, so that label data of small samples are expanded, and the negative influence of false samples of the pseudo labels on the model is reduced by using an adaptive weight l. With the proceeding of the training process, the obtained network classification accuracy is gradually increased, and the problem processing capability of the model is gradually enhanced. Compared with an existing remote sensing image classification method, the method does not depend on a large number of labeled images any more, very high classification accuracy can be obtained under the condition of small samples, and the method has deeper practical significance.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and relates to a self-learning small-sample remote-sensing image classification method based on consistency constraints. A method for few-shot remote sensing image classification tasks. Background technique [0002] As an important branch of remote sensing image processing technology, remote sensing image classification task has become one of the core technologies for military and civilian use. Due to the rapid development of remote sensing imaging and digital computing technology, the management method of manually classifying and labeling massive remote sensing images has been far from meeting the needs of applications. On the one hand, a large amount of training data makes manual labeling too expensive; on the other hand, it is easy to produce one-sided labeling due to too much reliance on human subjective consciousness. Therefore, it is of great practical significance...

AI Technical Summary

Problems solved by technology

However, the background of remote sensing images is complex, and there are usually interferences of salient objects similar to the images. Traditional features do not have a strong ability to distinguish, and it is easy to cause misjudgment of categories.

In addition, this method relies on a large number of labeled training quantities, and manual labeling causes a lot of waste of resources

Images