Zero-shot Learning with Cross-Layer Neural Network for Emitter Pattern Recognition

The existing emitter pattern recognition methods depend on a large number of labeled samples and are unable to handle unknown samples. Zero-shot Learning (ZSL) can migrate from source classes to target categories by learning a common embedding space, thus realizing the generalization to unknown samples. In this paper, a novel Cross-Layer Neural Network (CLNN) is proposed that integrates different embedding methods into an end-to-end deep learning architecture. The experimental results demonstrate that the proposed method can achieve excellent performances in the presence of unseen radar patterns with either new feature combinations or new feature ranges.

[1]  Zhongfei Zhang,et al.  Manifold regularized cross-modal embedding for zero-shot learning , 2017, Inf. Sci..

[2]  Alessandro Laio,et al.  Clustering by fast search and find of density peaks , 2014, Science.

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

[4]  Bernt Schiele,et al.  Learning Deep Representations of Fine-Grained Visual Descriptions , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Shunsheng Zhang,et al.  Radar emitter signal recognition based on time-frequency analysis , 2013 .

[6]  Tao Guo,et al.  Adaptive Affinity Propagation Clustering , 2008, ArXiv.

[7]  Christoph H. Lampert,et al.  Learning to detect unseen object classes by between-class attribute transfer , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Soma Biswas,et al.  Preserving Semantic Relations for Zero-Shot Learning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Lindsay Cain,et al.  Convolutional neural networks for radar emitter classification , 2018, 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC).

[10]  Tao Xiang,et al.  Learning a Deep Embedding Model for Zero-Shot Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Jing Xu,et al.  A Comprehensive Estimation Method for Kernel Function of Radar Signal Classifier , 2015 .

[12]  Gexiang Zhang,et al.  Radar emitter signal recognition based on support vector machines , 2004, ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004..

[13]  Shaogang Gong,et al.  Unsupervised Domain Adaptation for Zero-Shot Learning , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[14]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Venkatesh Saligrama,et al.  Zero-Shot Learning via Semantic Similarity Embedding , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[16]  Marc'Aurelio Ranzato,et al.  DeViSE: A Deep Visual-Semantic Embedding Model , 2013, NIPS.

[17]  L. Anjaneyulu,et al.  Radar emitter classification using self-organising Neural Network models , 2008, 2008 International Conference on Recent Advances in Microwave Theory and Applications.

[18]  Jan Matuszewski,et al.  The knowledge based approach for emitter identification , 1998, 12th International Conference on Microwaves and Radar. MIKON-98. Conference Proceedings (IEEE Cat. No.98EX195).

[19]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[20]  Cong Peng,et al.  Recognition Algorithm of Emitter Signals Based on PCA+CNN , 2018, 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC).