End-to-End Data Visualization by Metric Learning and Coordinate Transformation

This paper presents a deep nonlinear metric learning framework for data visualization on an image dataset. We propose the Triangular Similarity and prove its equivalence to the Cosine Similarity in measuring a data pair. Based on this novel similarity, a geometrically motivated loss function - the triangular loss - is then developed for optimizing a metric learning system comprising two identical CNNs. It is shown that this deep nonlinear system can be efficiently trained by a hybrid algorithm based on the conventional backpropagation algorithm. More interestingly, benefiting from classical manifold learning theories, the proposed system offers two different views to visualize the outputs, the second of which provides better classification results than the state-of-the-art methods in the visualizable spaces.

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

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[3]  Li Bai,et al.  Cosine Similarity Metric Learning for Face Verification , 2010, ACCV.

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

[5]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[6]  Amir Globerson,et al.  Metric Learning by Collapsing Classes , 2005, NIPS.

[7]  Nicholas J. Higham,et al.  INVERSE PROBLEMS NEWSLETTER , 1991 .

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

[9]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.

[10]  H. R. Morton,et al.  Introduction to Topology , 1964, The Mathematical Gazette.

[11]  John C. Platt,et al.  Learning Discriminative Projections for Text Similarity Measures , 2011, CoNLL.

[12]  Atilla Baskurt,et al.  Triangular similarity metric learning for face verification , 2015, 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG).

[13]  Yann LeCun,et al.  Convolutional networks and applications in vision , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

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

[15]  Yoram Singer,et al.  Online and batch learning of pseudo-metrics , 2004, ICML.

[16]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[17]  Bin Ma,et al.  Acoustic TextTiling for story segmentation of spoken documents , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[19]  Samy Bengio,et al.  An Online Algorithm for Large Scale Image Similarity Learning , 2009, NIPS.

[20]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[21]  Geoffrey E. Hinton,et al.  Neighbourhood Components Analysis , 2004, NIPS.

[22]  Éric Gaussier,et al.  Online and Batch Learning of Generalized Cosine Similarities , 2009, 2009 Ninth IEEE International Conference on Data Mining.

[23]  Navdeep Jaitly,et al.  Towards End-To-End Speech Recognition with Recurrent Neural Networks , 2014, ICML.

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

[25]  Samuel Berlemont,et al.  Siamese neural network based similarity metric for inertial gesture classification and rejection , 2015, 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG).

[26]  Ke Chen,et al.  Extracting Speaker-Specific Information with a Regularized Siamese Deep Network , 2011, NIPS.

[27]  Inderjit S. Dhillon,et al.  Information-theoretic metric learning , 2006, ICML '07.

[28]  Stefan Duffner,et al.  Siamese multi-layer perceptrons for dimensionality reduction and face identification , 2015, Multimedia Tools and Applications.

[29]  Hossein Mobahi,et al.  Deep learning from temporal coherence in video , 2009, ICML '09.

[30]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[31]  Yann LeCun,et al.  Toward automatic phenotyping of developing embryos from videos , 2005, IEEE Transactions on Image Processing.

[32]  Samy Bengio,et al.  Large Scale Online Learning of Image Similarity through Ranking , 2009, IbPRIA.

[33]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[34]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

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

[36]  Cordelia Schmid,et al.  Is that you? Metric learning approaches for face identification , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[37]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

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

[39]  Fei-Fei Li,et al.  Hierarchical semantic indexing for large scale image retrieval , 2011, CVPR 2011.

[40]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[41]  Pierre Baldi,et al.  Neural Networks for Fingerprint Recognition , 1993, Neural Computation.

[42]  Joo-Hwee Lim,et al.  Similarity Learning for Nearest Neighbor Classification , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[43]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[44]  Andrew Zisserman,et al.  Fisher Vector Faces in the Wild , 2013, BMVC.

[45]  Tomer Hertz,et al.  Learning a Mahalanobis Metric from Equivalence Constraints , 2005, J. Mach. Learn. Res..