Discriminative Histogram Intersection Metric Learning and Its Applications

In this paper, a novel method called discriminative histogram intersection metric learning (DHIML) is proposed for pair matching and classification. Specifically, we introduce a discrimination term for learning a metric from binary information such as same/not-same or similar/dissimilar, and then combine it with the classification error for the discrimination in classifier construction. Compared with conventional approaches, the proposed method has several advantages. 1) The histogram intersection strategy is adopted into metric learning to deal with the widely used histogram features effectively. 2) By introducing discriminative term and classification error term into metric learning, a more discriminative distance metric and a classifier can be learned together. 3) The objective function is robust to outliers and noises for both features and labels in the training. The performance of the proposed method is tested on four applications: face verification, face-track identification, face-track clustering, and image classification. Evaluations on the challenging restricted protocol of Labeled Faces in the Wild (LFW) benchmark, a dataset with more than 7 000 face-tracks, and Caltech-101 dataset validate the robustness and discriminability of the proposed metric learning, compared with the recent state-of-the-art approaches.

[1]  Yunjun Gao,et al.  Efficient Metric All-k-Nearest-Neighbor Search on Datasets Without Any Index , 2016, Journal of Computer Science and Technology.

[2]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[3]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[4]  John G. Daugman,et al.  Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression , 1988, IEEE Trans. Acoust. Speech Signal Process..

[5]  James M. Rehg,et al.  Beyond the Euclidean distance: Creating effective visual codebooks using the Histogram Intersection Kernel , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[6]  Bao-Gang Hu,et al.  Robust feature extraction via information theoretic learning , 2009, ICML '09.

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

[8]  Tam Le,et al.  Unsupervised Riemannian Metric Learning for Histograms Using Aitchison Transformations , 2015, ICML.

[9]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

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

[11]  Tal Hassner,et al.  Multiple One-Shots for Utilizing Class Label Information , 2009, BMVC.

[12]  Weifeng Liu,et al.  Correntropy: Properties and Applications in Non-Gaussian Signal Processing , 2007, IEEE Transactions on Signal Processing.

[13]  Sei-ichiro Kamata,et al.  Efficient Large-Scale Video Retrieval via Discriminative Signatures , 2013, IEICE Trans. Inf. Syst..

[14]  Tal Hassner,et al.  Similarity Scores Based on Background Samples , 2009, ACCV.

[15]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[16]  Jason J. Corso,et al.  Efficient max-margin metric learning , 2012 .

[17]  David Avis,et al.  Ground metric learning , 2011, J. Mach. Learn. Res..

[18]  Leonidas J. Guibas,et al.  Supervised Earth Mover's Distance Learning and Its Computer Vision Applications , 2012, ECCV.

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

[20]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Shaoning Zeng,et al.  Weighted average integration of sparse representation and collaborative representation for robust face recognition , 2016, Computational Visual Media.

[22]  Peyman Milanfar,et al.  Face Verification Using the LARK Representation , 2011, IEEE Transactions on Information Forensics and Security.

[23]  Larry S. Davis,et al.  Learning a discriminative dictionary for sparse coding via label consistent K-SVD , 2011, CVPR 2011.

[24]  Larry S. Davis,et al.  Discriminative Dictionary Learning with Pairwise Constraints , 2012, ACCV.

[25]  Baoli Li,et al.  Traffic-Sign Detection and Classification in the Wild , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[27]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

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

[29]  Kaizhu Huang,et al.  GSML: A Unified Framework for Sparse Metric Learning , 2009, 2009 Ninth IEEE International Conference on Data Mining.