Affiliation:
1. Faculty of Computing, Harbin Institute of Technology, No. 92, Xidazhi Street, Nangang District, Harbin 150001, China
Abstract
Feature extraction is an important process for the automatic recognition of synthetic aperture radar targets, but the rising complexity of the recognition network means that the features are abstractly implied in the network parameters and the performances are difficult to attribute. We propose the modern synergetic neural network (MSNN), which transforms the feature extraction process into the prototype self-learning process by the deep fusion of an autoencoder (AE) and a synergetic neural network. We prove that nonlinear AEs (e.g., stacked and convolutional AE) with ReLU activation functions reach the global minimum when their weights can be divided into tuples of M-P inverses. Therefore, MSNN can use the AE training process as a novel and effective nonlinear prototypes self-learning module. In addition, MSNN improves learning efficiency and performance stability by making the codes spontaneously converge to one-hots with the dynamics of Synergetics instead of loss function manipulation. Experiments on the MSTAR dataset show that MSNN achieves state-of-the-art recognition accuracy. The feature visualization results show that the excellent performance of MSNN stems from the prototype learning to capture features that are not covered in the dataset. These representative prototypes ensure the accurate recognition of new samples.
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference40 articles.
1. Nonparametric Bayesian Attributed Scattering Center Extraction for Synthetic Aperture Radar Targets;Cong;IEEE Trans. Signal Process.,2016
2. Target detection and recognition in SAR imagery based on KFDA;Gao;J. Syst. Eng. Electron.,2015
3. SAR Imagery Feature Extraction Using 2DPCA-Based Two-Dimensional Neighborhood Virtual Points Discriminant Embedding;Pei;IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.,2016
4. Song, S., Xu, B., and Yang, J. (2016). SAR target recognition via supervised discriminative dictionary learning and sparse representation of the SAR-HOG feature. Remote Sens., 8.
5. Reducing the dimensionality of data with neural networks;Hinton;Science,2006
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献