Hyperspectral Classification Using Deep Belief Networks Based on Conjugate Gradient Update and Pixel-Centric Spectral Block Features

This article describes the use of deep belief networks (DBNs) based on the conjugate gradient (CG) update algorithm for hyperspectral classification. DBNs perform two processes: unsupervised pretraining and supervised fine-tuning. The parameter update method in the fine-tuning stage plays a key role in optimizing the classification model. The proposed method employs CG-based fine-tuning to avoid the “zig-zagging” problem with the gradient descent algorithm and to accelerate the DBN convergence. First, the spectral features and pixel-centric spectral block features are extracted from hyperspectral images for use as the input vectors. The update variables are then calculated based on a CG algorithm and the 2-norm, and the parameters are updated during the backpropagation step of the proposed CGDBN. Two models with different CG methods are applied to a public hyperspectral image benchmark for classification experiments and analysis, and the results are compared with those from several classification methods that are currently in use. The experimental results show that the proposed classification models have advantages in terms of model convergence and low sensitivity to certain parameters. In addition, application to a hyperspectral image of coastal wetlands in the Yellow River Delta produces a satisfactory classification. The results of this study demonstrate that the proposed CG-update-based DBN provides a new approach for hyperspectral dataset classification.

[1]  Peng Liu,et al.  Ieee Journal of Selected Topics in Applied Earth Observations and Remote Sensing 1 Active Deep Learning for Classification of Hyperspectral Images , 2022 .

[2]  Geoffrey E. Hinton A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[3]  C. M. Reeves,et al.  Function minimization by conjugate gradients , 1964, Comput. J..

[4]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[5]  Fang Tang,et al.  Deep Learning With Grouped Features for Spatial Spectral Classification of Hyperspectral Images , 2017, IEEE Geoscience and Remote Sensing Letters.

[6]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[7]  Pradeep Dubey,et al.  Distributed Deep Learning Using Synchronous Stochastic Gradient Descent , 2016, ArXiv.

[8]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[9]  Jon Atli Benediktsson,et al.  Deep Learning for Hyperspectral Image Classification: An Overview , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Deyu Meng,et al.  Hyperspectral Image Classification With Markov Random Fields and a Convolutional Neural Network , 2017, IEEE Transactions on Image Processing.

[11]  Xiwen Lu,et al.  A conjugate gradient method with descent direction for unconstrained optimization , 2009, J. Comput. Appl. Math..

[12]  Qian Du,et al.  Hyperspectral Classification Based on Texture Feature Enhancement and Deep Belief Networks , 2018, Remote. Sens..

[13]  Jie Liu,et al.  Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting , 2015, IEEE Journal of Selected Topics in Signal Processing.

[14]  Jianjun Lei,et al.  Joint spatial-spectral hyperspectral image classification based on convolutional neural network , 2020, Pattern Recognit. Lett..

[15]  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.

[16]  Pedram Ghamisi,et al.  Heterogeneous Transfer Learning for Hyperspectral Image Classification Based on Convolutional Neural Network , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[17]  Y. Nesterov A method for unconstrained convex minimization problem with the rate of convergence o(1/k^2) , 1983 .

[18]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[19]  Chenming Li,et al.  Deep Belief Network for Spectral–Spatial Classification of Hyperspectral Remote Sensor Data , 2019, Sensors.

[20]  Nicolas Le Roux,et al.  Representational Power of Restricted Boltzmann Machines and Deep Belief Networks , 2008, Neural Computation.

[21]  Raymond Y. K. Lau,et al.  Hyperspectral Image Classification With Deep Learning Models , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Bidyut Baran Chaudhuri,et al.  HybridSN: Exploring 3-D–2-D CNN Feature Hierarchy for Hyperspectral Image Classification , 2019, IEEE Geoscience and Remote Sensing Letters.

[23]  Ping Zhong,et al.  A Hybrid DBN and CRF Model for Spectral-Spatial Classification of Hyperspectral Images , 2017 .

[24]  Léon Bottou,et al.  Stochastic Gradient Descent Tricks , 2012, Neural Networks: Tricks of the Trade.

[25]  Jin Chen,et al.  A DBN for hyperspectral remote sensing image classification , 2017, 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[26]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[27]  Boris Polyak The conjugate gradient method in extreme problems , 2015 .

[28]  Pabitra Mitra,et al.  BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[29]  Shutao Li,et al.  Learning to Diversify Deep Belief Networks for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Matthew D. Zeiler ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[31]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[32]  Linmi Tao,et al.  Multiple deep-belief-network-based spectral-spatial classification of hyperspectral images , 2019, Tsinghua Science and Technology.

[33]  Jonathan Cheung-Wai Chan,et al.  Collaborative learning of lightweight convolutional neural network and deep clustering for hyperspectral image semi-supervised classification with limited training samples , 2020 .

[34]  Ning Qian,et al.  On the momentum term in gradient descent learning algorithms , 1999, Neural Networks.

[35]  Gang Wang,et al.  Spectral-spatial classification of hyperspectral image using autoencoders , 2013, 2013 9th International Conference on Information, Communications & Signal Processing.