A spatial-spectral semisupervised deep learning framework using siamese networks and angular loss

Abstract Deep learning has gained popularity in recent times in the field of feature-extraction, object-identification, object-tracking, change-detection, image-classification, spatio-temporal-data analysis, and hyperspectral imaging. Most of the supervised tasks using deep learning require a large number of labeled samples, barring which the model tends to overfit and do not generalize well to the test data. Semi-supervised learning is very beneficial for hyperspectral images which contain abundant unlabeled data samples in comparison to labeled data. Furthermore, it is known that for datasets in which samples are related to each other in all three dimensions such as videos, three-dimensional biological images and hyperspectral images, the use of spatial–spectral/spatial–temporal based deep learning strategies, which can exploit the relationship between pixels in all three-dimensions, has also seen a rise in the past few years. Moreover, to date, deep feature extraction and classification has been done using euclidean distance based metrics. Foray into the field of angular feature extraction and classification, which is known to work better when samples are impacted by resolution or illumination differences, has not yet been made. We propose a novel spatial–spectral semisupervised deep learning approach based on angular distances by projecting the deep features onto the surface of an l 2 -normalized unit hypersphere.

[1]  Geoffrey E. Hinton,et al.  The Helmholtz Machine , 1995, Neural Computation.

[2]  Michael I. Jordan,et al.  Variational inference for Dirichlet process mixtures , 2006 .

[3]  Saurabh Prasad,et al.  Angular Discriminant Analysis for Hyperspectral Image Classification , 2015, IEEE Journal of Selected Topics in Signal Processing.

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Hao Wu,et al.  Semi-Supervised Deep Learning Using Pseudo Labels for Hyperspectral Image Classification , 2018, IEEE Transactions on Image Processing.

[6]  Shin Ishii,et al.  Distributional Smoothing with Virtual Adversarial Training , 2015, ICLR 2016.

[7]  Marc'Aurelio Ranzato,et al.  Semi-supervised learning of compact document representations with deep networks , 2008, ICML '08.

[8]  Lorenzo Bruzzone,et al.  A Novel Transductive SVM for Semisupervised Classification of Remote-Sensing Images , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[10]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[11]  Luis Gómez-Chova,et al.  Semisupervised Image Classification With Laplacian Support Vector Machines , 2008, IEEE Geoscience and Remote Sensing Letters.

[12]  Alexander Zien,et al.  Semi-Supervised Classification by Low Density Separation , 2005, AISTATS.

[13]  Tapani Raiko,et al.  Semi-supervised Learning with Ladder Networks , 2015, NIPS.

[14]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[15]  Mikhail Belkin,et al.  Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples , 2006, J. Mach. Learn. Res..

[16]  Quoc V. Le,et al.  Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis , 2011, CVPR 2011.

[17]  Jason Weston,et al.  Semisupervised Neural Networks for Efficient Hyperspectral Image Classification , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Zoubin Ghahramani,et al.  Learning from labeled and unlabeled data with label propagation , 2002 .

[19]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

[20]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Ying Li,et al.  Spectral-Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network , 2017, Remote. Sens..

[22]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[23]  Hossein Mobahi,et al.  Deep Learning via Semi-supervised Embedding , 2012, Neural Networks: Tricks of the Trade.

[24]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

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

[26]  Xiuping Jia,et al.  Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[27]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[28]  Zoubin Ghahramani,et al.  Unsupervised and Constrained Dirichlet Process Mixture Models for Verb Clustering , 2009 .

[29]  Bernhard Schölkopf,et al.  Cluster Kernels for Semi-Supervised Learning , 2002, NIPS.

[30]  Jeffrey Pennington,et al.  Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions , 2011, EMNLP.

[31]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[32]  Joseph J. Atick,et al.  Towards a Theory of Early Visual Processing , 1990, Neural Computation.