Feedback mechanism based iterative metric learning for person re-identification

Abstract Person re-identification problem is targeting to match people in the views of non-overlapped camera networks. It is an important task in the fields of computer vision and video surveillance. It shows great value in applications like surveillance and action recognition. Existing metric learning based methods measure the similarity of sample pairs by learning a metric space in which the positive pairs are closer than negative pairs. However, the appearance features undergo with drastic variation. Person re-identification is a typical small sample problem. It is hard to learn a robust projection of metric subspace that takes all the situations into consideration. The learned metric subspace is usually over-fitting to training dataset due to the strict metric learning constraint. And the hard pairs in training dataset will weaken the discrimination of matching pairs’ similarity. To address these problems, a feedback mechanism based iterative metric learning method is proposed. The proposed method introduces a mean distance of multi-metric subspace to deal with the over-fitting problem. The joint discriminant optimal model on feedback top ranks matching pairs will enhance the discrimination of matching pairs’ similarity. It is a robust and discriminative distance metric which measures the matching pairs similarity with distances of multiple metric projections learned by a set of training datasets. Aiming to learn the multi-metric subspace, the proposed method gives a feedback mechanism based approach which back propagates the top ranks identification results as pseudo training datasets. The effectiveness of proposed mean distance of multi-metric projection is analyzed and proved theoretically. And extensive experiments on three challenging datasets, VIPeR, GRID and CUHK01 are conducted. The results show that the proposed method achieves the best performance and improves the state-of-the-art rank-1 identification rates by 18.48%, 2.00% and 5.41% on three datasets respectively.

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

[2]  Shengcai Liao,et al.  Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[3]  Yong Luo,et al.  Decomposition-Based Transfer Distance Metric Learning for Image Classification , 2014, IEEE Transactions on Image Processing.

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

[5]  Baowen Xu,et al.  Super-resolution Person re-identification with semi-coupled low-rank discriminant dictionary learning , 2015, CVPR.

[6]  Hai Tao,et al.  Evaluating Appearance Models for Recognition, Reacquisition, and Tracking , 2007 .

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

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

[9]  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).

[10]  Shaogang Gong,et al.  Person re-identification by probabilistic relative distance comparison , 2011, CVPR 2011.

[11]  Shih-Chia Huang,et al.  Highly Accurate Moving Object Detection in Variable Bit Rate Video-Based Traffic Monitoring Systems , 2013, IEEE Transactions on Neural Networks and Learning Systems.

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

[13]  Chunxiao Liu,et al.  On-the-fly feature importance mining for person re-identification , 2014, Pattern Recognit..

[14]  Ehud Rivlin,et al.  Color Invariants for Person Reidentification , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Xiao Liu,et al.  Semi-supervised Coupled Dictionary Learning for Person Re-identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Alfredo Petrosino,et al.  Salient feature based graph matching for person re-identification , 2015, Pattern Recognit..

[17]  Huchuan Lu,et al.  Sample-Specific SVM Learning for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

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

[21]  Xiao Liu,et al.  Attribute-restricted latent topic model for person re-identification , 2012, Pattern Recognit..

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

[23]  William Robson Schwartz,et al.  CBRA: Color-based ranking aggregation for person re-identification , 2015, ICIP.

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

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

[26]  Chunxiao Liu,et al.  Person Re-identification: What Features Are Important? , 2012, ECCV Workshops.

[27]  Farida Cheriet,et al.  Modified Large Margin Nearest Neighbor Metric Learning for Regression , 2014, IEEE Signal Processing Letters.

[28]  Subhransu Maji,et al.  Bilinear CNNs for Fine-grained Visual Recognition , 2015 .

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

[30]  Tao Xiang,et al.  Unsupervised Learning of Generative Topic Saliency for Person Re-identification , 2014, BMVC.

[31]  Xiaogang Wang,et al.  Person Re-identification by Salience Matching , 2013, 2013 IEEE International Conference on Computer Vision.

[32]  Victor S. Lempitsky,et al.  Multi-Region bilinear convolutional neural networks for person re-identification , 2015, 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

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

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

[35]  Alexandros Iosifidis,et al.  View-Invariant Action Recognition Based on Artificial Neural Networks , 2012, IEEE Transactions on Neural Networks and Learning Systems.

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

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

[38]  Shengcai Liao,et al.  Deep Metric Learning for Person Re-identification , 2014, 2014 22nd International Conference on Pattern Recognition.

[39]  Xiaogang Wang,et al.  DeepReID: Deep Filter Pairing Neural Network for Person Re-identification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

[41]  Jiwen Lu,et al.  Learning Compact Binary Face Descriptor for Face Recognition , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  Alberto Del Bimbo,et al.  Matching People across Camera Views using Kernel Canonical Correlation Analysis , 2014, ICDSC.

[43]  Shaogang Gong,et al.  Learning a Discriminative Null Space for Person Re-identification , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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