Semi-Supervised Generative Adversarial Nets with Multiple Generators for SAR Image Recognition

As an important model of deep learning, semi-supervised learning models are based on Generative Adversarial Nets (GANs) and have achieved a competitive performance on standard optical images. However, the training of GANs becomes unstable when they are applied to SAR images, which reduces the feature extraction capability of the discriminator in GANs. This paper presents a new semi-supervised GANs with Multiple generators and a classifier (MCGAN). This model improves the stability of training for SAR images by employing multiple generators. A multi-classifier is introduced to the new GANs to utilize the labeled images during the training of the GANs, which shares the low level layers with the discriminator. Then, the layers of the trained discriminator and the classifier construct the recognition network for SAR images after having been finely tuned using a small number of the labeled images. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) databases show that the proposed recognition network achieves a better and more stable recognition performance than several traditional semi-supervised methods as well as other GANs-based semi-supervised methods.

[1]  Na Wang,et al.  Multiple model particle filter track-before-detect for range ambiguous radar , 2013 .

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

[3]  Wei Li,et al.  Multi-Aspect-Aware Bidirectional LSTM Networks for Synthetic Aperture Radar Target Recognition , 2017, IEEE Access.

[4]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[5]  Jacob Abernethy,et al.  On Convergence and Stability of GANs , 2018 .

[6]  A. Coletta,et al.  COSMO-SkyMed an existing opportunity for observing the Earth , 2010 .

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

[8]  Minh N. Do,et al.  Semantic Image Inpainting with Perceptual and Contextual Losses , 2016, ArXiv.

[9]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

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

[11]  Marc'Aurelio Ranzato,et al.  Building high-level features using large scale unsupervised learning , 2011, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[12]  Sheng Yu,et al.  Stratified pooling based deep convolutional neural networks for human action recognition , 2017, Multimedia Tools and Applications.

[13]  Simon Wagner.  Combination of convolutional feature extraction and support vector machines for radar ATR , 2014, 17th International Conference on Information Fusion (FUSION).

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

[15]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[17]  B. Scholkopf,et al.  Fisher discriminant analysis with kernels , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[18]  Hongwei Liu,et al.  Convolutional Neural Network With Data Augmentation for SAR Target Recognition , 2016, IEEE Geoscience and Remote Sensing Letters.

[19]  Trung Le,et al.  MGAN: Training Generative Adversarial Nets with Multiple Generators , 2018, ICLR.

[20]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[21]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[22]  Paul D. Bates,et al.  Near Real-Time Flood Detection in Urban and Rural Areas Using High-Resolution Synthetic Aperture Radar Images , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[24]  Bernhard Schölkopf,et al.  Learning with Local and Global Consistency , 2003, NIPS.

[25]  Erfu Yang,et al.  Dual-Branch Deep Convolution Neural Network for Polarimetric SAR Image Classification , 2017 .

[26]  Simon Wagner,et al.  Morphological Component Analysis in SAR images to improve the generalization of ATR systems , 2015, 2015 3rd International Workshop on Compressed Sensing Theory and its Applications to Radar, Sonar and Remote Sensing (CoSeRa).

[27]  Léon Bottou,et al.  Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[28]  Haipeng Wang,et al.  SAR target recognition based on deep learning , 2014, 2014 International Conference on Data Science and Advanced Analytics (DSAA).

[29]  Yueting Zhang,et al.  Synthetic Aperture Radar Image Synthesis by Using Generative Adversarial Nets , 2017, IEEE Geoscience and Remote Sensing Letters.

[30]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[31]  Rob Fergus,et al.  Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks , 2015, NIPS.

[32]  Jost Tobias Springenberg,et al.  Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks , 2015, ICLR.