Marginal Stacked Autoencoder With Adaptively-Spatial Regularization for Hyperspectral Image Classification

Stacked autoencoder (SAE) provides excellent performance for image processing under sufficient training samples. However, the collection of training samples is difficult in hyperspectral images. Insufficient training samples easily make SAE overfit and limit the application of SAE to hypersepctral images. To address this problem, a novel marginal SAE with adaptively-spatial regularization (ARMSAE) is proposed for hyperspectral image classification. First, a superpixel segmentation method is used to divide the image into many homogenous regions. Then, at the pretraining stage, an adaptively-shaped spatial regularization is introduced to extract contextual information of samples in the homogenous regions. It sufficiently utilizes unlabeled adjacent samples to alleviate the lack of training samples. At the fine-tuning stage, the marginal samples based on geometrical property are selected to tune the ARMSAE network. The fine-tuning exploits margin strategy to alleviate the inaccurate statistical estimation caused by insufficient training samples. Finally, the label of each test sample is determined by all the samples locating in the same homogenous region. Experimental results on hyperspectral images demonstrate the proposed method provides encouraging classification performance compared with several related state-of-the-art methods.

[1]  Massimo Zucchetti,et al.  A survey of landmine detection using hyperspectral imaging , 2017 .

[2]  Junwei Han,et al.  Novel Folded-PCA for improved feature extraction and data reduction with hyperspectral imaging and SAR in remote sensing , 2014 .

[3]  Jochen J. Steil,et al.  Online learning and generalization of parts-based image representations by non-negative sparse autoencoders , 2012, Neural Networks.

[4]  James E. Fowler,et al.  Locality-Preserving Discriminant Analysis in Kernel-Induced Feature Spaces for Hyperspectral Image Classification , 2011, IEEE Geoscience and Remote Sensing Letters.

[5]  James E. Fowler,et al.  Locality-Preserving Dimensionality Reduction and Classification for Hyperspectral Image Analysis , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Bor-Chen Kuo,et al.  Feature Mining for Hyperspectral Image Classification , 2013, Proceedings of the IEEE.

[7]  Peter Glöckner,et al.  Why Does Unsupervised Pre-training Help Deep Learning? , 2013 .

[8]  Fang Liu,et al.  Imbalanced Hyperspectral Image Classification Based on Maximum Margin , 2015, IEEE Geoscience and Remote Sensing Letters.

[9]  Yansheng Li,et al.  Unsupervised Spectral–Spatial Feature Learning With Stacked Sparse Autoencoder for Hyperspectral Imagery Classification , 2015, IEEE Geoscience and Remote Sensing Letters.

[10]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[11]  José M. Bioucas-Dias,et al.  Bayesian Hyperspectral Image Segmentation With Discriminative Class Learning , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Mathieu Fauvel,et al.  Fast Forward Feature Selection of Hyperspectral Images for Classification With Gaussian Mixture Models , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[13]  Juha Suomalainen,et al.  Generation of Spectral–Temporal Response Surfaces by Combining Multispectral Satellite and Hyperspectral UAV Imagery for Precision Agriculture Applications , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[14]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[15]  Sen Jia,et al.  Convolutional neural networks for hyperspectral image classification , 2017, Neurocomputing.

[16]  Jing Wang,et al.  Independent component analysis-based dimensionality reduction with applications in hyperspectral image analysis , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Hong Li,et al.  Hyperspectral Image Classification Using Functional Data Analysis , 2014, IEEE Transactions on Cybernetics.

[18]  Yi Shen,et al.  Convolutional neural network based classification for hyperspectral data , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[19]  Lin Sun,et al.  Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold , 2015, Neurocomputing.

[20]  Qian Du,et al.  Multisource Remote Sensing Data Classification Based on Convolutional Neural Network , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Kang Sun,et al.  A New Band Selection Method for Hyperspectral Image Based on Data Quality , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[22]  Tian Han,et al.  Investigation of Nonlinearity in Hyperspectral Imagery Using Surrogate Data Methods , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Zhen Wang,et al.  Hessian Regularized Sparse Coding for Human Action Recognition , 2015, MMM.

[24]  Rama Chellappa,et al.  Entropy rate superpixel segmentation , 2011, CVPR 2011.

[25]  Xing Zhao,et al.  Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief Network , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[26]  Gang Wang,et al.  Deep Learning-Based Classification of Hyperspectral Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[27]  G. F. Hughes,et al.  On the mean accuracy of statistical pattern recognizers , 1968, IEEE Trans. Inf. Theory.

[28]  Chunhui Zhao,et al.  Anomaly Detection in Hyperspectral Imagery Based on Kernel ICA Feature Extraction , 2008, 2008 Second International Symposium on Intelligent Information Technology Application.

[29]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[30]  Jun Yu,et al.  Coupled Deep Autoencoder for Single Image Super-Resolution , 2017, IEEE Transactions on Cybernetics.

[31]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[32]  Wei Li,et al.  Transferred Deep Learning for Anomaly Detection in Hyperspectral Imagery , 2017, IEEE Geoscience and Remote Sensing Letters.

[33]  Jon Atli Benediktsson,et al.  Kernel Principal Component Analysis for the Classification of Hyperspectral Remote Sensing Data over Urban Areas , 2009, EURASIP J. Adv. Signal Process..

[34]  Qingquan Li,et al.  A 3-D Gabor Phase-Based Coding and Matching Framework for Hyperspectral Imagery Classification , 2018, IEEE Transactions on Cybernetics.

[35]  Claude Cariou,et al.  A new k-nearest neighbor density-based clustering method and its application to hyperspectral images , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[36]  Jiankun Hu,et al.  Superpixel-Based Graphical Model for Remote Sensing Image Mapping , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[37]  Wai Keung Wong,et al.  Deep Learning Regularized Fisher Mappings , 2011, IEEE Transactions on Neural Networks.

[38]  Qian Du,et al.  Hyperspectral Image Classification Using Deep Pixel-Pair Features , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[39]  Chein-I. Chang.  Hyperspectral Data Exploitation: Theory and Applications , 2007 .

[40]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote sensing images with support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[41]  Stephen Lin,et al.  Marginal Fisher Analysis and Its Variants for Human Gait Recognition and Content- Based Image Retrieval , 2007, IEEE Transactions on Image Processing.

[42]  Licheng Jiao,et al.  Hyperspectral Band Selection Based on Trivariate Mutual Information and Clonal Selection , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[43]  Peijun Du,et al.  Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging , 2016, Neurocomputing.

[44]  Chunxia Zhang,et al.  Generalized extreme learning machine autoencoder and a new deep neural network , 2017, Neurocomputing.

[45]  Yitian Xu,et al.  Maximum Margin of Twin Spheres Support Vector Machine for Imbalanced Data Classification , 2017, IEEE Transactions on Cybernetics.

[46]  Antonio J. Plaza,et al.  Semisupervised Hyperspectral Image Segmentation Using Multinomial Logistic Regression With Active Learning , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[47]  Stephen Lin,et al.  Graph Embedding and Extensions: A General Framework for Dimensionality Reduction , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[48]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[49]  Thomas Cudahy,et al.  Hyperspectral imaging spectroscopy of a Mars analogue environment at the North Pole Dome, Pilbara Craton, Western Australia , 2005, 1401.5201.

[50]  Brajesh Kumar,et al.  Spectral Contextual Classification of Hyperspectral Imagery With Probabilistic Relaxation Labeling , 2017, IEEE Transactions on Cybernetics.

[51]  Licheng Jiao,et al.  Multiple Kernel Learning Based on Discriminative Kernel Clustering for Hyperspectral Band Selection , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[52]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[53]  Yushi Chen,et al.  Supervised Locally Linear Embedding based dimension reduction for hyperspectral image classification , 2013, 2013 IEEE International Geoscience and Remote Sensing Symposium - IGARSS.