A Remote Sensing Image Classification Method Based on Pruned Compression Neural Network

Abstract

The invention discloses a remote sensing image classification method based on pruning compression neural network, which comprises: training an initial neural network model for remote sensing image recognition problems, using the model as the initial model to be pruned; using the initial model to learn Calculate the sensitivity matrix of the parameters in the model layer by layer based on the sensitivity of the output function of the parameter to small changes in the parameters; sort the values ​​of the sensitivity matrix of the parameters, and prune out the unimportant parameters; retrain the remaining weights that have not been pruned; After one layer of pruning is completed, repeat the steps for the pruning process of the next layer; use the pruned neural network model to classify remote sensing images. The method of the present invention provides a more accurate, practical and reliable method to calculate the importance of each parameter in the model, thereby eliminating those unimportant parameters, and finally obtaining a satisfactory compression ratio for more efficient remote sensing Image classification and recognition.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing and recognition, in particular to a remote sensing image classification method based on a pruned compression neural network. Background technique [0002] In recent years, deep neural networks have made major breakthroughs in the fields of remote sensing target recognition and remote sensing image classification. However, although the performance of deep learning models is very powerful, the existing deep learning models have huge parameters and complex network structures. Therefore, It will bring difficulties in both computing and storage, and it is difficult to deploy to mobile devices or embedded devices with limited memory and computing resources. Studies have shown that deep learning models have serious over-parameterization problems. Not all parameters play a role in the model. Some parameters have limited functions, redundant expressions, and even reduce the performa...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the object of the present invention is to provide a remote sensing image classification method based on pruning and compression neural network, which can effectively solve the problem of huge parameter quantity and high computational complexity in the process of remote sensing image classification by deep neural network model. The problem makes the pruned and compressed neural network model more efficient in the classification of remote sensing images

Images