Distribution Shift Metric Learning for Fine-Grained Ship Classification in SAR Images

Fine-grained ship classification in synthetic aperture radar (SAR) images is a challenging task, since SAR images can only provide limited discriminative information due to the limitation of SAR imaging mechanism. Distance metric learning (DML) methods have the ability to improve the discriminative ability of the feature representations through preserving the supervisory information of ship samples. In this article, we proposed a novel DML method, termed as distribution shift metric learning (DML-ds), which improves the original Laplacian regularized metric learning by adding an interclass distribution shift regularization term. Extensive experiments and in-depth analysis demonstrate that the proposed DML-ds can effectively increase the interclass separability and the intraclass compactness, thereby improving the fine-grained ship classification performance in SAR images, and outperforms most of state-of-the-art methods.

[1]  Bernard De Baets,et al.  An approach to supervised distance metric learning based on difference of convex functions programming , 2018, Pattern Recognit..

[2]  Bernard De Baets,et al.  Distance metric learning for ordinal classification based on triplet constraints , 2017, Knowl. Based Syst..

[3]  Feiping Nie,et al.  Learning a Mahalanobis distance metric for data clustering and classification , 2008, Pattern Recognit..

[4]  Haitao Lang,et al.  Distance metric learning for ship classification in SAR images , 2018, Remote Sensing.

[5]  Xi Zhang,et al.  Ship Classification in SAR Image by Joint Feature and Classifier Selection , 2016, IEEE Geoscience and Remote Sensing Letters.

[6]  Jian Yang,et al.  Ship Classification Based on MSHOG Feature and Task-Driven Dictionary Learning with Structured Incoherent Constraints in SAR Images , 2018, Remote. Sens..

[7]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[8]  Di Zhao,et al.  Hierarchical ship detection and recognition with high-resolution polarimetric synthetic aperture radar imagery , 2014 .

[9]  Domenico Velotto,et al.  Ship Classification in TerraSAR-X Images With Convolutional Neural Networks , 2018, IEEE Journal of Oceanic Engineering.

[10]  FengJiashi,et al.  A survey on deep learning-based fine-grained object classification and semantic segmentation , 2017 .

[11]  Marc Sebban,et al.  A Survey on Metric Learning for Feature Vectors and Structured Data , 2013, ArXiv.

[12]  Lei Guo,et al.  Exploring Hierarchical Convolutional Features for Hyperspectral Image Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Rong Jin,et al.  Regularized Distance Metric Learning: Theory and Algorithm , 2009, NIPS.

[14]  Bernard De Baets,et al.  Supervised distance metric learning through maximization of the Jeffrey divergence , 2017, Pattern Recognit..

[15]  Haitao Lang,et al.  Ship Classification in SAR Images Improved by AIS Knowledge Transfer , 2018, IEEE Geoscience and Remote Sensing Letters.

[16]  Lei Wang,et al.  Positive Semidefinite Metric Learning with Boosting , 2009, NIPS.

[17]  I. Hajnsek,et al.  A tutorial on synthetic aperture radar , 2013, IEEE Geoscience and Remote Sensing Magazine.

[18]  Haitao Lang,et al.  Distribution Discrepancy Maximization Metric Learning for Ship Classification in Synthetic Aperture Radar Images , 2019, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium.

[19]  Michael I. Jordan,et al.  Distance Metric Learning with Application to Clustering with Side-Information , 2002, NIPS.

[20]  Hong Zhang,et al.  Fine-grained ship classification based on deep residual learning for high-resolution SAR images , 2019, Remote Sensing Letters.

[21]  Lei Guo,et al.  When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[22]  LiuWei,et al.  Semi-supervised distance metric learning for collaborative image retrieval and clustering , 2010 .

[23]  Bo Zhang,et al.  A Novel Hierarchical Ship Classifier for COSMO-SkyMed SAR Data , 2014, IEEE Geoscience and Remote Sensing Letters.

[24]  Huanxin Zou,et al.  Ship Classification in TerraSAR-X Images With Feature Space Based Sparse Representation , 2013, IEEE Geoscience and Remote Sensing Letters.

[25]  Haitao Lang,et al.  Ship Classification in Moderate-Resolution SAR Image by Naive Geometric Features-Combined Multiple Kernel Learning , 2017, IEEE Geoscience and Remote Sensing Letters.

[26]  Peng Li,et al.  Similarity Metric Learning for Face Recognition , 2013, 2013 IEEE International Conference on Computer Vision.

[27]  David Zhang,et al.  A Kernel Classification Framework for Metric Learning , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[28]  Ye Yuan,et al.  Joint Convolutional Neural Network for Small-Scale Ship Classification in SAR Images , 2019, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium.

[29]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[30]  Lianru Gao,et al.  Deep CNN With Multi-Scale Rotation Invariance Features for Ship Classification , 2018, IEEE Access.

[31]  Gerard Margarit,et al.  Ship Classification in Single-Pol SAR Images Based on Fuzzy Logic , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[32]  Kaizhu Huang,et al.  Sparse Metric Learning via Smooth Optimization , 2009, NIPS.

[33]  Peng Li,et al.  Distance Metric Learning with Eigenvalue Optimization , 2012, J. Mach. Learn. Res..