Kernel Distance Metric Learning Using Pairwise Constraints for Person Re-Identification

Person re-identification is a fundamental task in many computer vision and image understanding systems. Due to appearance variations from different camera views, person re-identification still poses an important challenge. In the literature, KISSME has already been introduced as an effective distance metric learning method using pairwise constraints to improve the re-identification performance. Computationally, it only requires two inverse covariance matrix estimations. However, the linear transformation induced by KISSME is not powerful enough for more complex problems. We show that KISSME can be kernelized, resulting in a nonlinear transformation, which is suitable for many real-world applications. Moreover, the proposed kernel method can be used for learning distance metrics from structured objects without having a vectorial representation. The effectiveness of our method is validated on five publicly available data sets. To further apply the proposed kernel method efficiently when data are collected sequentially, we introduce a fast incremental version that learns a dissimilarity function in the feature space without estimating the inverse covariance matrices. The experiments show that the latter variant can obtain competitive results in a computationally efficient manner.

[1]  Zhen Li,et al.  Learning Locally-Adaptive Decision Functions for Person Verification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Nanning Zheng,et al.  Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Ming-Hsuan Yang,et al.  An Ensemble Color Model for Human Re-identification , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[4]  Shishir K. Shah,et al.  A survey of approaches and trends in person re-identification , 2014, Image Vis. Comput..

[5]  Bernard De Baets,et al.  Supervised distance metric learning through maximization of the Jeffrey divergence , 2017, Pattern Recognit..

[6]  Horst Bischof,et al.  Mahalanobis Distance Learning for Person Re-identification , 2014, Person Re-Identification.

[7]  Alex Pentland,et al.  Bayesian face recognition , 2000, Pattern Recognit..

[8]  Thomas Gärtner,et al.  On Graph Kernels: Hardness Results and Efficient Alternatives , 2003, COLT.

[9]  Xuelong Li,et al.  Person Reidentification by Minimum Classification Error-Based KISS Metric Learning , 2015, IEEE Transactions on Cybernetics.

[10]  Michael Collins,et al.  Convolution Kernels for Natural Language , 2001, NIPS.

[11]  Shengcai Liao,et al.  Large Scale Similarity Learning Using Similar Pairs for Person Verification , 2016, AAAI.

[12]  Stephen Lin,et al.  Graph Embedding and Extensions: A General Framework for Dimensionality Reduction , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[14]  Shaogang Gong,et al.  Associating Groups of People , 2009, BMVC.

[15]  Shengcai Liao,et al.  Person re-identification by Local Maximal Occurrence representation and metric learning , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Kaare Brandt Petersen,et al.  The Matrix Cookbook , 2006 .

[17]  Horst Bischof,et al.  Relaxed Pairwise Learned Metric for Person Re-identification , 2012, ECCV.

[18]  Hai Tao,et al.  Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features , 2008, ECCV.

[19]  Mingli Song,et al.  Manifold Ranking-Based Matrix Factorization for Saliency Detection , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[20]  Horst Bischof,et al.  Large scale metric learning from equivalence constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Shaogang Gong,et al.  Person Re-Identification by Support Vector Ranking , 2010, BMVC.

[22]  Frédéric Jurie,et al.  PCCA: A new approach for distance learning from sparse pairwise constraints , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Dapeng Tao,et al.  Deep Multi-View Feature Learning for Person Re-Identification , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[24]  Michael Jones,et al.  An improved deep learning architecture for person re-identification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Sergio A. Velastin,et al.  Local Fisher Discriminant Analysis for Pedestrian Re-identification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

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

[27]  Anton van den Hengel,et al.  Learning to rank in person re-identification with metric ensembles , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[29]  Inderjit S. Dhillon,et al.  Metric and Kernel Learning Using a Linear Transformation , 2009, J. Mach. Learn. Res..

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

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

[32]  Shaogang Gong,et al.  Reidentification by Relative Distance Comparison , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  Zhihua Wei,et al.  QRKISS: A Two-Stage Metric Learning via QR-Decomposition and KISS for Person Re-Identification , 2018, Neural Processing Letters.

[34]  Eleazar Eskin,et al.  The Spectrum Kernel: A String Kernel for SVM Protein Classification , 2001, Pacific Symposium on Biocomputing.

[35]  J. Friedman.  Regularized Discriminant Analysis , 1989 .

[36]  Lei Wang,et al.  Positive Semidefinite Metric Learning Using Boosting-like Algorithms , 2011, J. Mach. Learn. Res..

[37]  Rita Cucchiara,et al.  3DPeS: 3D people dataset for surveillance and forensics , 2011, J-HGBU '11.

[38]  Xiaogang Wang,et al.  Person Re-Identification by Saliency Learning , 2014 .

[39]  Shengcai Liao,et al.  Salient Color Names for Person Re-identification , 2014, ECCV.

[40]  Xinbo Gao,et al.  Tensor Rank Preserving Discriminant Analysis for Facial Recognition , 2018, IEEE Transactions on Image Processing.

[41]  Vittorio Murino,et al.  Custom Pictorial Structures for Re-identification , 2011, BMVC.

[42]  Fei Xiong,et al.  Person Re-Identification Using Kernel-Based Metric Learning Methods , 2014, ECCV.

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

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

[45]  Liang Lin,et al.  Deep feature learning with relative distance comparison for person re-identification , 2015, Pattern Recognit..

[46]  Feiping Nie,et al.  A general kernelization framework for learning algorithms based on kernel PCA , 2010, Neurocomputing.

[47]  Jian-Huang Lai,et al.  Deep Ranking for Person Re-Identification via Joint Representation Learning , 2015, IEEE Transactions on Image Processing.

[48]  Alberto Del Bimbo,et al.  Person Re-Identification by Iterative Re-Weighted Sparse Ranking , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[49]  Huchuan Lu,et al.  Person Re-Identification via Distance Metric Learning With Latent Variables , 2017, IEEE Transactions on Image Processing.

[50]  Xiaogang Wang,et al.  Human Reidentification with Transferred Metric Learning , 2012, ACCV.

[51]  Matti Pietikäinen,et al.  Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[52]  Narendra Ahuja,et al.  Pedestrian Recognition with a Learned Metric , 2010, ACCV.

[53]  Yuan Yan Tang,et al.  Person Re-Identification by Dual-Regularized KISS Metric Learning , 2016, IEEE Transactions on Image Processing.

[54]  Andrew Zisserman,et al.  Efficient Additive Kernels via Explicit Feature Maps , 2012, IEEE Trans. Pattern Anal. Mach. Intell..

[55]  Zia-ur Rahman,et al.  Properties and performance of a center/surround retinex , 1997, IEEE Trans. Image Process..

[56]  Xiaogang Wang,et al.  Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[57]  Yunhong Wang,et al.  Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities , 2015, IEEE Transactions on Image Processing.

[58]  Bingpeng Ma,et al.  Local Descriptors Encoded by Fisher Vectors for Person Re-identification , 2012, ECCV Workshops.

[59]  Horst Bischof,et al.  Person Re-identification by Efficient Impostor-Based Metric Learning , 2012, 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance.