Polyhedral Conic Classifiers for Computer Vision Applications and Open Set Recognition

This paper introduces a family of quasi-linear discriminants that outperform current large-margin methods in sliding window visual object detection and open set recognition tasks. In these applications, the classification problems are both numerically imbalanced – positive (object class) training and test windows are much rarer than negative (non-class) ones – and geometrically asymmetric – the positive samples typically form compact, visually-coherent groups while negatives are much more diverse, including anything at all that is not a well-centered sample from the target class. For such tasks, there is a need for discriminants whose decision regions focus on tightly circumscribing the positive class, while still taking account of negatives in zones where the two classes overlap. To this end, we propose a family of quasi-linear “polyhedral conic” discriminants whose positive regions are distorted <inline-formula><tex-math notation="LaTeX">$L_1$</tex-math><alternatives><mml:math><mml:msub><mml:mi>L</mml:mi><mml:mn>1</mml:mn></mml:msub></mml:math><inline-graphic xlink:href="cevikalp-ieq1-2934455.gif"/></alternatives></inline-formula> or <inline-formula><tex-math notation="LaTeX">$L_2$</tex-math><alternatives><mml:math><mml:msub><mml:mi>L</mml:mi><mml:mn>2</mml:mn></mml:msub></mml:math><inline-graphic xlink:href="cevikalp-ieq2-2934455.gif"/></alternatives></inline-formula> balls. In addition, we also integrated the proposed classification loss into deep neural networks so that both the features and classifier can be learned simultaneously end-to-end fashion to improve the classification accuracies. The methods have properties and run-time complexities comparable to linear Support Vector Machines (SVMs), and they can be trained from either binary or positive-only samples using constrained quadratic programs related to SVMs. Our experiments show that they significantly outperform linear SVMs, deep neural networks using softmax loss function and existing one-class discriminants on a wide range of object detection, face verification, open set recognition and conventional closed-set classification tasks.

[1]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Yoram Singer,et al.  Pegasos: primal estimated sub-gradient solver for SVM , 2011, Math. Program..

[3]  Xavier Gastaldi,et al.  Shake-Shake regularization , 2017, ArXiv.

[4]  Thomas Mensink,et al.  Image Classification with the Fisher Vector: Theory and Practice , 2013, International Journal of Computer Vision.

[5]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[6]  Hakan Cevikalp,et al.  Hyperdisk based large margin classifier , 2013, Pattern Recognit..

[7]  Bruce A. Draper,et al.  The challenge of face recognition from digital point-and-shoot cameras , 2013, 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS).

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

[9]  Yangqing Jia,et al.  Deep Convolutional Ranking for Multilabel Image Annotation , 2013, ICLR.

[10]  Murat Dundar,et al.  Polyhedral classifier for target detection: a case study: colorectal cancer , 2008, ICML '08.

[11]  Reshma Khemchandani,et al.  Twin Support Vector Machines for Pattern Classification , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Glenn Fung,et al.  Proximal support vector machine classifiers , 2001, KDD '01.

[13]  Erik Learned-Miller,et al.  FDDB: A benchmark for face detection in unconstrained settings , 2010 .

[14]  Hakan Cevikalp,et al.  Visual Object Detection Using Cascades of Binary and One-Class Classifiers , 2017, International Journal of Computer Vision.

[15]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[16]  S. Hussain,et al.  Machine Learning Methods for Visual Object Detection , 2012 .

[17]  Terrance E. Boult,et al.  The Extreme Value Machine , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Terrance E. Boult,et al.  Probability Models for Open Set Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Annabella Astorino,et al.  Polyhedral Separability Through Successive LP , 2002 .

[20]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[21]  Benjamin Recht,et al.  Random Features for Large-Scale Kernel Machines , 2007, NIPS.

[22]  Naresh Manwani,et al.  Learning Polyhedral Classifiers Using Logistic Function , 2010, ACML.

[23]  Naresh Manwani,et al.  Polyceptron: A Polyhedral Learning Algorithm , 2011, ArXiv.

[24]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

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

[26]  Jiri Matas,et al.  Weighted Sampling for Large-Scale Boosting , 2008, BMVC.

[27]  Hakan Cevikalp,et al.  Efficient object detection using cascades of nearest convex model classifiers , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Anderson Rocha,et al.  Toward Open Set Recognition , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Sören Sonnenburg,et al.  Optimized Cutting Plane Algorithm for Large-Scale Risk Minimization , 2009, J. Mach. Learn. Res..

[30]  Hakan Cevikalp,et al.  Best Fitting Hyperplanes for Classification , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[32]  Bill Triggs,et al.  Feature Sets and Dimensionality Reduction for Visual Object Detection , 2010, BMVC.

[33]  Hakan Cevikalp,et al.  Polyhedral Conic Classifiers for Visual Object Detection and Classification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[35]  Adil M. Bagirov,et al.  Max–min separability , 2005, Optim. Methods Softw..

[36]  Refail Kasimbeyli,et al.  A novel piecewise linear classifier based on polyhedral conic and max–min separabilities , 2011, TOP.

[37]  Chandan Srivastava,et al.  Support Vector Data Description , 2011 .

[38]  Nir Ailon,et al.  Deep Metric Learning Using Triplet Network , 2014, SIMBAD.

[39]  Kristin P. Bennett,et al.  Duality and Geometry in SVM Classifiers , 2000, ICML.

[40]  Shiguang Shan,et al.  Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[42]  Olvi L. Mangasarian,et al.  Multisurface proximal support vector machine classification via generalized eigenvalues , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[43]  Bernt Schiele,et al.  What Makes for Effective Detection Proposals? , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Benjamin Graham,et al.  Fractional Max-Pooling , 2014, ArXiv.

[45]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[46]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

[47]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

[48]  Andrew Zisserman,et al.  Efficient additive kernels via explicit feature maps , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[49]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[50]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[51]  Ling Huang,et al.  Large-Margin Convex Polytope Machine , 2014, NIPS.

[52]  Xudong Jiang,et al.  Human Detection by Quadratic Classification on Subspace of Extended Histogram of Gradients , 2014, IEEE Transactions on Image Processing.

[53]  Rafail N. Gasimov,et al.  Separation via polyhedral conic functions , 2006, Optim. Methods Softw..

[54]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[55]  Hakan Cevikalp,et al.  Face and landmark detection by using cascade of classifiers , 2013, 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG).