Adversarial Deep Domain Adaptation for Multi-Band SAR Images Classification

Deep convolutional neural networks (CNNs) have made a breakthrough on supervised SAR images classification. However, SAR imaging is considerably affected by the frequency band. That means a neural network trained on a SAR image set of one band is not suitable for the classification of another band images. As manually labeling the training samples of each band is always time-consuming, we propose an unsupervised multi-level domain adaptation method based on adversarial learning to solve the problem of multi-band SAR images classification. First, we train a discriminative CNN using samples of one frequency band data set that contains labels to map the data to a latent feature space. Then, we adjust the trained CNN to map the unlabeled samples of another frequency band data set to the same feature space through alternately optimizing two adversarial loss functions. Thus, the features of these two band images are fused and can be classified by the same classifier. We checked the performance of our method using both simulated data and measured data. Our method made a breakthrough in the classification of multi-band images with accuracies of 99% on both data sets. The results are even very close to the supervised CNN trained using a large number of labeled samples.

[1]  Zongxu Pan,et al.  Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data , 2017, Remote. Sens..

[2]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[3]  Gangyao Kuang,et al.  SAR Image Classification by Exploiting Adaptive Contextual Information and Composite Kernels , 2018, IEEE Geoscience and Remote Sensing Letters.

[4]  David A. Clausi,et al.  Operational SAR Sea-Ice Image Classification , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Michael I. Jordan,et al.  Deep Transfer Learning with Joint Adaptation Networks , 2016, ICML.

[6]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[7]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Trevor Darrell,et al.  Deep Domain Confusion: Maximizing for Domain Invariance , 2014, CVPR 2014.

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

[10]  George Trigeorgis,et al.  Domain Separation Networks , 2016, NIPS.

[11]  Kouichi Sakurai,et al.  One Pixel Attack for Fooling Deep Neural Networks , 2017, IEEE Transactions on Evolutionary Computation.

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

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

[14]  Hod Lipson,et al.  Understanding Neural Networks Through Deep Visualization , 2015, ArXiv.

[15]  Huanxin Zou,et al.  Region-Based Classification of SAR Images Using Kullback–Leibler Distance Between Generalized Gamma Distributions , 2015, IEEE Geoscience and Remote Sensing Letters.

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

[17]  Akira Hirose,et al.  Complex-Valued Neural Networks: Advances and Applications , 2013 .

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

[19]  François Laviolette,et al.  Domain-Adversarial Neural Networks , 2014, ArXiv.

[20]  Laurens van der Maaten,et al.  Barnes-Hut-SNE , 2013, ICLR.

[21]  Mingsheng Liao,et al.  Nonlinear Compressed Sensing-Based LDA Topic Model for Polarimetric SAR Image Classification , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

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

[23]  Michael I. Jordan,et al.  Learning Transferable Features with Deep Adaptation Networks , 2015, ICML.

[24]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

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

[26]  Gabriela Palacio,et al.  Unsupervised Classification of SAR Images Using Markov Random Fields and ${\cal G}_{I}^{0}$ Model , 2011, IEEE Geoscience and Remote Sensing Letters.

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

[28]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[29]  Malcolm Davidson,et al.  A Closed-Form Expression Relating Classification Accuracy to SAR System Calibration Uncertainty , 2009, IEEE Geoscience and Remote Sensing Letters.

[30]  Jin Zhao,et al.  SAR Image Classification via Hierarchical Sparse Representation and Multisize Patch Features , 2016, IEEE Geoscience and Remote Sensing Letters.

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

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

[33]  Hong Zhang,et al.  Combining single shot multibox detector with transfer learning for ship detection using Sentinel-1 images , 2017, 2017 SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA).

[34]  Xiao Bai,et al.  Ground Target Classification in Noisy SAR Images Using Convolutional Neural Networks , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[35]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).