Robust matching and recognition using context-dependent kernels

The success of kernel methods including support vector machines (SVMs) strongly depends on the design of appropriate kernels. While initially kernels were designed in order to handle fixed-length data, their extension to unordered, variable-length data became more than necessary for real pattern recognition problems such as object recognition and bioinformatics. We focus in this paper on object recognition using a new type of kernel referred to as "context-dependent". Objects, seen as constellations of local features (interest points, regions, etc.), are matched by minimizing an energy function mixing (1) a fidelity term which measures the quality of feature matching, (2) a neighborhood criterion which captures the object geometry and (3) a regularization term. We will show that the fixed-point of this energy is a "context-dependent" kernel ("CDK") which also satisfies the Mercer condition. Experiments conducted on object recognition show that when plugging our kernel in SVMs, we clearly outperform SVMs with "context-free" kernels.

[1]  Jian-Yun Nie,et al.  Cross-language information retrieval based on parallel texts and automatic mining of parallel texts from the Web , 1999, SIGIR '99.

[2]  Barbara Caputo,et al.  Recognition with local features: the kernel recipe , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[3]  Nuno Vasconcelos,et al.  A Kullback-Leibler Divergence Based Kernel for SVM Classification in Multimedia Applications , 2003, NIPS.

[4]  David Haussler,et al.  Convolution kernels on discrete structures , 1999 .

[5]  Jitendra Malik,et al.  Shape Context: A New Descriptor for Shape Matching and Object Recognition , 2000, NIPS.

[6]  Claus Bahlmann,et al.  Online handwriting recognition with support vector machines - a kernel approach , 2002, Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition.

[7]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[8]  Hichem Sahbi,et al.  Consensus Network Decoding for Statistical Machine Translation System Combination , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[9]  Linda G. Shapiro,et al.  A SIFT descriptor with global context , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[11]  Nicu Sebe,et al.  Fast spatial pattern discovery integrating boosting with constellations of contextual descriptors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[13]  Hichem Sahbi,et al.  Context-dependent kernel design for object matching and recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Thomas Gärtner,et al.  A survey of kernels for structured data , 2003, SKDD.

[15]  Tamir Hazan,et al.  Algebraic Set Kernels with Application to Inference Over Local Image Representations , 2004, NIPS.

[16]  Vapnik,et al.  SVMs for Histogram Based Image Classification , 1999 .

[17]  David Haussler,et al.  Using the Fisher Kernel Method to Detect Remote Protein Homologies , 1999, ISMB.

[18]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[19]  Marco Cuturi.  Etude de noyaux de semigroupe pour objets structurés dans le cadre de l'apprentissage statistique , 2005 .

[20]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.

[21]  Submission and Formatting Instructions for Icml 2016 , 2022 .

[22]  Siwei Lyu,et al.  Mercer kernels for object recognition with local features , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

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

[24]  Trevor Darrell,et al.  The Pyramid Match Kernel: Efficient Learning with Sets of Features , 2007, J. Mach. Learn. Res..

[25]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[26]  Cordelia Schmid,et al.  Semi-Local Affine Parts for Object Recognition , 2004, BMVC.

[27]  Tony Jebara,et al.  A Kernel Between Sets of Vectors , 2003, ICML.

[28]  Bernhard Schölkopf,et al.  Kernel Methods in Computational Biology , 2005 .

[29]  N. Boujemaa,et al.  The intermediate matching kernel for image local features , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[30]  Lior Wolf,et al.  Learning over Sets using Kernel Principal Angles , 2003, J. Mach. Learn. Res..

[31]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[32]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Patrick Haffner,et al.  Support vector machines for histogram-based image classification , 1999, IEEE Trans. Neural Networks.

[34]  Daniel Marcu,et al.  Statistical Phrase-Based Translation , 2003, NAACL.

[35]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[36]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[37]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[38]  Francesca Odone,et al.  Hausdorff Kernel for 3D Object Acquisition and Detection , 2002, ECCV.