A Review of the Autoencoder and Its Variants: A Comparative Perspective from Target Recognition in Synthetic-Aperture Radar Images

In recent years, unsupervised feature learning based on a neural network architecture has become a hot new topic for research [1]-[4]. The revival of interest in such deep networks can be attributed to the development of efficient optimization skills, by which the model parameters can be optimally estimated [5]. The milestone work done by Hinton and Salakhutdinov [6] proposes to initialize the weights that allow deep autoencoder networks to learn lowdimensional codes. The encoding trick introduced works much better than principal component analysis (PCA) in terms of dimension reduction.

[1]  Marios Savvides,et al.  Correlation Pattern Recognition for Face Recognition , 2006, Proceedings of the IEEE.

[2]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[3]  Licheng Jiao,et al.  Recursive Autoencoders-Based Unsupervised Feature Learning for Hyperspectral Image Classification , 2017, IEEE Geoscience and Remote Sensing Letters.

[4]  J. Chris McGlone,et al.  Fusion of HYDICE hyperspectral data with panchromatic imagery for cartographic feature extraction , 1999, IEEE Trans. Geosci. Remote. Sens..

[5]  Raghu G. Raj,et al.  SAR Automatic Target Recognition Using Discriminative Graphical Models , 2014, IEEE Transactions on Aerospace and Electronic Systems.

[6]  Mihai Datcu,et al.  Contextual Descriptors for Scene Classes in Very High Resolution SAR Images , 2012, IEEE Geoscience and Remote Sensing Letters.

[7]  Shiming Xiang,et al.  Automatic Road Detection and Centerline Extraction via Cascaded End-to-End Convolutional Neural Network , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Naif Alajlan,et al.  Reconstructing Cloud-Contaminated Multispectral Images With Contextualized Autoencoder Neural Networks , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Emre Ertin,et al.  Through-the-Wall SAR Attributed Scattering Center Feature Estimation , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Lee C. Potter,et al.  Attributed scattering centers for SAR ATR , 1997, IEEE Trans. Image Process..

[11]  Xin Huang,et al.  Unsupervised Deep Feature Learning for Urban Village Detection from High-Resolution Remote Sensing Images , 2017 .

[12]  Bhagavatula Vijaya Kumar,et al.  Performance of the extended maximum average correlation height (EMACH) filter and the polynomial distance classifier correlation filter (PDCCF) for multiclass SAR detection and classification , 2002, SPIE Defense + Commercial Sensing.

[13]  Jordi Inglada,et al.  A New Statistical Similarity Measure for Change Detection in Multitemporal SAR Images and Its Extension to Multiscale Change Analysis , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Lei Guo,et al.  Effective and Efficient Midlevel Visual Elements-Oriented Land-Use Classification Using VHR Remote Sensing Images , 2015, IEEE Transactions on Geoscience and Remote Sensing.

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

[16]  Na Wang,et al.  Sparse Representation of Monogenic Signal: With Application to Target Recognition in SAR Images , 2014, IEEE Signal Processing Letters.

[17]  Jun Li,et al.  Advanced Spectral Classifiers for Hyperspectral Images: A review , 2017, IEEE Geoscience and Remote Sensing Magazine.

[18]  Eric R. Keydel,et al.  MSTAR extended operating conditions: a tutorial , 1996, Defense, Security, and Sensing.

[19]  Hongwei Liu,et al.  Attributed Scattering Center Extraction Algorithm Based on Sparse Representation With Dictionary Refinement , 2017, IEEE Transactions on Antennas and Propagation.

[20]  Dorde T. Grozdic,et al.  Whispered Speech Recognition Using Deep Denoising Autoencoder and Inverse Filtering , 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[21]  Marc'Aurelio Ranzato,et al.  Efficient Learning of Sparse Representations with an Energy-Based Model , 2006, NIPS.

[22]  Yanqing Guo,et al.  Coupled Dictionary Learning for Target Recognition in SAR Images , 2017, IEEE Geoscience and Remote Sensing Letters.

[23]  Charles C. Kemp,et al.  A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational Autoencoder , 2017, IEEE Robotics and Automation Letters.

[24]  Dan Zhang,et al.  Stacked Sparse Autoencoder in PolSAR Data Classification Using Local Spatial Information , 2016, IEEE Geoscience and Remote Sensing Letters.

[25]  Lei Wang,et al.  Stacked Sparse Autoencoder Modeling Using the Synergy of Airborne LiDAR and Satellite Optical and SAR Data to Map Forest Above-Ground Biomass , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[26]  Shawki Areibi,et al.  Domain Adaptation Using Representation Learning for the Classification of Remote Sensing Images , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[27]  Pascal Vincent,et al.  Contractive Auto-Encoders: Explicit Invariance During Feature Extraction , 2011, ICML.

[28]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[29]  Francesca Bovolo,et al.  A Novel Technique Based on Deep Learning and a Synthetic Target Database for Classification of Urban Areas in PolSAR Data , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[30]  Junyu Dong,et al.  Encoding Spectral and Spatial Context Information for Hyperspectral Image Classification , 2017, IEEE Geoscience and Remote Sensing Letters.

[31]  Huanxin Zou,et al.  Synthetic Aperture Radar Target Recognition with Feature Fusion Based on a Stacked Autoencoder , 2017, Sensors.

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

[33]  Lorenzo Bruzzone,et al.  Two-Stream Deep Architecture for Hyperspectral Image Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[34]  Ganggang Dong,et al.  Classification on the monogenic scale space: application to target recognition in SAR image. , 2015, IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.

[35]  Rajat Raina,et al.  Self-taught learning: transfer learning from unlabeled data , 2007, ICML '07.

[36]  Haipeng Wang,et al.  Complex-Valued Convolutional Neural Network and Its Application in Polarimetric SAR Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[37]  Jie Geng,et al.  High-Resolution SAR Image Classification via Deep Convolutional Autoencoders , 2015, IEEE Geoscience and Remote Sensing Letters.

[38]  Renato J. Cintra,et al.  Analytic Expressions for Stochastic Distances Between Relaxed Complex Wishart Distributions , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[39]  Jayaraman J. Thiagarajan,et al.  Sparse representations for automatic target classification in SAR images , 2010, 2010 4th International Symposium on Communications, Control and Signal Processing (ISCCSP).

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

[41]  Roland Memisevic,et al.  The Potential Energy of an Autoencoder , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  Chuang Sun,et al.  Deep Coupling Autoencoder for Fault Diagnosis With Multimodal Sensory Data , 2018, IEEE Transactions on Industrial Informatics.

[43]  D. Nagesh Kumar,et al.  Spectral-spatial classification of hyperspectral data with mutual information based segmented stacked autoencoder approach , 2018 .

[44]  Marco Martorella,et al.  Automatic Target Recognition by Means of Polarimetric ISAR Images and Neural Networks , 2009, IEEE Trans. Geosci. Remote. Sens..

[45]  Hao Li,et al.  Prediction of Subsurface NMR T2 Distributions in a Shale Petroleum System Using Variational Autoencoder-Based Neural Networks , 2017, IEEE Geoscience and Remote Sensing Letters.

[46]  Huanxin Zou,et al.  Deep Convolutional Highway Unit Network for SAR Target Classification With Limited Labeled Training Data , 2017, IEEE Geoscience and Remote Sensing Letters.

[47]  Ronald Kemker,et al.  Self-Taught Feature Learning for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[48]  Jin Zhao,et al.  POLSAR Image Classification via Wishart-AE Model or Wishart-CAE Model , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[49]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[50]  Mariantonietta Zonno,et al.  Azimuth Antenna Maximum Likelihood Estimation by Persistent Point Scatterers in SAR Images , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[51]  Carlo Gatta,et al.  Unsupervised Deep Feature Extraction for Remote Sensing Image Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[52]  Biao Hou,et al.  Classification of Polarimetric SAR Images Using Multilayer Autoencoders and Superpixels , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

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

[54]  Xueming Qian,et al.  Semantic Annotation of High-Resolution Satellite Images via Weakly Supervised Learning , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[55]  Richard J. Murphy,et al.  A Physics-Based Deep Learning Approach to Shadow Invariant Representations of Hyperspectral Images , 2018, IEEE Transactions on Image Processing.

[56]  Yicong Zhou,et al.  Learning Hierarchical Spectral–Spatial Features for Hyperspectral Image Classification , 2016, IEEE Transactions on Cybernetics.

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

[58]  Zhipeng Liu,et al.  Adaptive boosting for SAR automatic target recognition , 2007, IEEE Transactions on Aerospace and Electronic Systems.

[59]  Na Wang,et al.  Classification via Sparse Representation of Steerable Wavelet Frames on Grassmann Manifold: Application to Target Recognition in SAR Image , 2017, IEEE Transactions on Image Processing.

[60]  Ram M. Narayanan,et al.  Classification via the Shadow Region in SAR Imagery , 2012, IEEE Transactions on Aerospace and Electronic Systems.

[61]  Gongjian Wen,et al.  Target Recognition in Synthetic Aperture Radar Images via Matching of Attributed Scattering Centers , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[62]  Haipeng Wang,et al.  Target Classification Using the Deep Convolutional Networks for SAR Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[63]  Guang-Bin Huang,et al.  Extreme Learning Machine for Multilayer Perceptron , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[64]  Fuchun Sun,et al.  Building feature space of extreme learning machine with sparse denoising stacked-autoencoder , 2016, Neurocomputing.

[65]  Anil M. Cheriyadat,et al.  Unsupervised Feature Learning for Aerial Scene Classification , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[66]  Akira Hirose,et al.  Unsupervised Fine Land Classification Using Quaternion Autoencoder-Based Polarization Feature Extraction and Self-Organizing Mapping , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[67]  Peijun Du,et al.  Mid-Level Feature Representation via Sparse Autoencoder for Remotely Sensed Scene Classification , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[68]  David Casasent,et al.  MINACE filter classification algorithms for ATR using MSTAR data , 2005, SPIE Defense + Commercial Sensing.

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

[70]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[71]  Leslie M. Novak,et al.  Performance of 10- and 20-target MSE classifiers , 2000, IEEE Trans. Aerosp. Electron. Syst..

[72]  S. Z. Gürbüz,et al.  Deep convolutional autoencoder for radar-based classification of similar aided and unaided human activities , 2018, IEEE Transactions on Aerospace and Electronic Systems.

[73]  Jin Zhao,et al.  Multilayer Projective Dictionary Pair Learning and Sparse Autoencoder for PolSAR Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[74]  Antonio J. Plaza,et al.  Active learning based autoencoder for hyperspectral imagery classification , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[75]  Yinglong Dai,et al.  Analyzing Tongue Images Using a Conceptual Alignment Deep Autoencoder , 2018, IEEE Access.

[76]  Yanxin Li,et al.  SAR Target Configuration Recognition Using Locality Preserving Property and Gaussian Mixture Distribution , 2013, IEEE Geoscience and Remote Sensing Letters.

[77]  Cheng Xiao,et al.  Automatic Target Recognition of SAR Images Based on Global Scattering Center Model , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[78]  Jie Geng,et al.  Spectral–Spatial Classification of Hyperspectral Image Based on Deep Auto-Encoder , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[79]  Zongxu Pan,et al.  An Improved Shape Contexts Based Ship Classification in SAR Images , 2017, Remote. Sens..

[80]  Randolph L. Moses,et al.  Feature extraction using attributed scattering center models on SAR imagery , 1999, Defense, Security, and Sensing.

[81]  Zhang Liangpei,et al.  Spatial-Spectral Unsupervised Convolutional Sparse Auto-Encoder Classifier for Hyperspectral Imagery , 2017 .

[82]  Tie Qiu,et al.  Remote Sensing Image Classification Based on Ensemble Extreme Learning Machine With Stacked Autoencoder , 2017, IEEE Access.

[83]  Shiguang Shan,et al.  Representation Learning with Smooth Autoencoder , 2014, ACCV.

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

[85]  Ling Shao,et al.  Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[86]  Jie Geng,et al.  Deep Supervised and Contractive Neural Network for SAR Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[87]  Maoguo Gong,et al.  A Multiobjective Sparse Feature Learning Model for Deep Neural Networks , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[88]  Emmanuel Trouvé,et al.  Multidate Divergence Matrices for the Analysis of SAR Image Time Series , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[89]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[91]  Hongwei Liu,et al.  SAR Automatic Target Recognition Based on Euclidean Distance Restricted Autoencoder , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[92]  Xiangrong Zhang,et al.  Hyperspectral image classification based on stacked marginal discriminative autoencoder , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[93]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[94]  Naif Alajlan,et al.  Using convolutional features and a sparse autoencoder for land-use scene classification , 2016 .

[95]  Qun Zhao,et al.  Support vector machines for SAR automatic target recognition , 2001 .

[96]  Shawn D. Newsam,et al.  Geographic Image Retrieval Using Local Invariant Features , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[97]  Gui-Song Xia,et al.  Extreme value theory-based calibration for the fusion of multiple features in high-resolution satellite scene classification , 2013 .

[98]  Geoffrey E. Hinton,et al.  Autoencoders, Minimum Description Length and Helmholtz Free Energy , 1993, NIPS.

[99]  Pasquale Iervolino,et al.  A Novel Ship Detector Based on the Generalized-Likelihood Ratio Test for SAR Imagery , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

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

[101]  Weihua Su,et al.  Deep Filter Banks for Land-Use Scene Classification , 2016, IEEE Geoscience and Remote Sensing Letters.

[102]  Bo Du,et al.  Saliency-Guided Unsupervised Feature Learning for Scene Classification , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[103]  Jun Yu,et al.  Multitask Autoencoder Model for Recovering Human Poses , 2018, IEEE Transactions on Industrial Electronics.

[104]  Dušan Gleich,et al.  Temporal Change Detection in SAR Images Using Log Cumulants and Stacked Autoencoder , 2018, IEEE Geoscience and Remote Sensing Letters.

[105]  Jürgen Schmidhuber,et al.  Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction , 2011, ICANN.

[106]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

[107]  Zhenfeng Shao,et al.  High-resolution remote-sensing imagery retrieval using sparse features by auto-encoder , 2015 .

[108]  Qian Song,et al.  Zero-Shot Learning of SAR Target Feature Space With Deep Generative Neural Networks , 2017, IEEE Geoscience and Remote Sensing Letters.