Abstract
Despite the promising progress made in recent years, person re-identification (re-ID) remains a challenging task due to the complex variations in human appearances from different camera views. For this challenging problem, a large variety of algorithms have been developed in the fully supervised setting, requiring access to a large amount of labeled training data. However, the main bottleneck for fully supervised re-ID is the limited availability of labeled training samples. To address this problem, we propose a self-trained subspace learning paradigm for person re-ID that effectively utilizes both labeled and unlabeled data to learn a discriminative subspace where person images across disjoint camera views can be easily matched. The proposed approach first constructs pseudo-pairwise relationships among unlabeled persons using the k-nearest neighbors algorithm. Then, with the pseudo-pairwise relationships, the unlabeled samples can be easily combined with the labeled samples to learn a discriminative projection by solving an eigenvalue problem. In addition, we refine the pseudo-pairwise relationships iteratively, which further improves learning performance. A multi-kernel embedding strategy is also incorporated into the proposed approach to cope with the non-linearity in a person’s appearance and explore the complementation of multiple kernels. In this way, the performance of person re-ID can be greatly enhanced when training data are insufficient. Experimental results on six widely used datasets demonstrate the effectiveness of our approach, and its performance can be comparable to the reported results of most state-of-the-art fully supervised methods while using much fewer labeled data.
- Ejaz Ahmed, Michael Jones, and Tim K. Marks. 2015. An improved deep learning architecture for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
- Le An, Songfan Yang, and Bir Bhanu. 2015. Person re-identification by robust canonical correlation analysis. IEEE Signal Processing Letters 22, 8, 1103--1107.Google Scholar
Cross Ref
- Davide Baltieri, Roberto Vezzani, and Rita Cucchiara. 2011. 3DPes: 3D people dataset for surveillance and forensics. In Proceedings of the International ACM Workshop on Multimedia Access to 3D Human Objects. 59--64. Google Scholar
Digital Library
- Sugato Basu, Arindam Banerjee, and Raymond Mooney. 2002. Semi-supervised clustering by seeding. In Proceedings of the International Conference on Machine Learning. Google Scholar
Digital Library
- Deng Cai, Xiaofei He, and Jiawei Han. 2007. Semi-supervised discriminant analysis. In Proceedings of the IEEE International Conference on Computer Vision. 1--7.Google Scholar
Cross Ref
- Olivier Chapelle, Bernhard Scholkopf, and Alexander Zien. 2009. Semi-supervised learning (Chapelle, O. et al., Eds.; 2006) {Book reviews}. IEEE Transactions on Neural Networks 20, 3, 542--542. Google Scholar
Digital Library
- Dapeng Chen, Zejian Yuan, Badong Chen, and Nanning Zheng. 2016b. Similarity learning with spatial constraints for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1268--1277.Google Scholar
Cross Ref
- S. Z. Chen, C. C. Guo, and J. H. Lai. 2016a. Deep ranking for person re-identification via joint representation learning. IEEE Transactions on Image Processing 25, 5, 2353--2367.Google Scholar
Digital Library
- Ying-Cong Chen, Wei-Shi Zheng, and Jianhuang Lai. 2015. Mirror representation for modeling view-specific transform in person re-identification. In Proceedings of the 24th International Conference on Artificial Intelligence. 3402--3408. Google Scholar
Digital Library
- Ying-Cong Chen, Wei-Shi Zheng, Jianhuang Lai, and Pong Yuen. 2016. An asymmetric distance model for cross-view feature mapping in person re-identification. IEEE Transactions on Circuits and Systems for Video Technology PP, 99, 1.Google Scholar
- De Cheng, Yihong Gong, Sanping Zhou, Jinjun Wang, and Nanning Zheng. 2016. Person re-identification by multi-channel parts-based CNN with improved triplet loss function. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1335--1344.Google Scholar
Cross Ref
- D. Figueira, L. Bazzani, H. Q. Minh, M. Cristani, A. Bernardino, and V. Murino. 2013. Semi-supervised multi-feature learning for person re-identification. In Proceedings of the IEEE International Conference on Advanced Video and Signal Based Surveillance. 111--116.Google Scholar
- Douglas Gray and Hai Tao. 2008. Viewpoint invariant pedestrian recognition with an ensemble of localized features. In Proceedings of the European Conference on Computer Vision. 262--275. Google Scholar
Digital Library
- Xiaofei He and Partha Niyogi. 2003. Locality preserving projections. In Advances in Neural Information Processing Systems 16.Google Scholar
- Martin Hirzer, Csaba Beleznai, Peter M. Roth, and Horst Bischof. 2011. Person re-identification by descriptive and discriminative classification. In Proceedings of the Scandinavian Conference on Image Analysis. 91--102. Google Scholar
Digital Library
- Steven C. H. Hoi, Wei Liu, and Shih-Fu Chang. 2008. Semi-supervised distance metric learning for collaborative image retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1--7.Google Scholar
Cross Ref
- Weiming Hu, Min Hu, Xue Zhou, Tieniu Tan, Jianguang Lou, and Steve Maybank. 2006. Principal axis-based correspondence between multiple cameras for people tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence 28, 4, 663--671. Google Scholar
Digital Library
- Svebor Karaman, Giuseppe Lisanti, Andrew D. Bagdanov, and Alberto Del Bimbo. 2014. Leveraging local neighborhood topology for large scale person re-identification. Pattern Recognition 47, 12, 3767--3778.Google Scholar
Cross Ref
- Elyor Kodirov, Tao Xiang, Zhenyong Fu, and Shaogang Gong. 2016. Person re-identification by unsupervised l1 graph learning. In Proceedings of the European Conference on Computer Vision. 178--195.Google Scholar
- Elyor Kodirov, Tao Xiang, and Shaogang Gong. 2015. Dictionary learning with iterative Laplacian regularisation for unsupervised person re-identification. In Proceedings of the 26th British Machine Vision Conference, Vol. 3. 8.Google Scholar
Cross Ref
- Martin Kostinger, Martin Hirzer, Paul Wohlhart, Peter M. Roth, and Horst Bischof. 2012. Large scale metric learning from equivalence constraints. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2288--2295. Google Scholar
Digital Library
- I. Kviatkovsky, A. Adam, and E. Rivlin. 2013. Color invariants for person reidentification. IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 7, 1622--1634. Google Scholar
Digital Library
- Sheng Li, Shao Ming, and Yun Fu. 2015. Cross-view projective dictionary learning for person re-identification. In Proceedings of the 24th International Joint Conference on Artificial Intelligence. Google Scholar
Digital Library
- Wei Li, Rui Zhao, and Xiaogang Wang. 2012. Human reidentification with transferred metric learning. In Proceedings of the Asian Conference on Computer Vision. 31--44. Google Scholar
Digital Library
- Weixin Li, Vijay Mahadevan, and Nuno Vasconcelos. 2014. Anomaly detection and localization in crowded scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence 36, 1, 18--32. Google Scholar
Digital Library
- Zhen Li, Shiyu Chang, Feng Liang, Thomas S. Huang, Liangliang Cao, and John R. Smith. 2013. Learning locally-adaptive decision functions for person verification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3610--3617. Google Scholar
Digital Library
- Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z. Li. 2015. Person re-identification by local maximal occurrence representation and metric learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2197--2206.Google Scholar
- Shengcai Liao and Stan Z. Li. 2015. Efficient PSD constrained asymmetric metric learning for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 3685--3693. Google Scholar
Digital Library
- Yutian Lin, Liang Zheng, Zhedong Zheng, Yu Wu, and Yi Yang. 2017. Improving person re-identification by attribute and identity learning. arXiv:1703.07220.Google Scholar
- Giuseppe Lisanti, Svebor Karaman, and Iacopo Masi. 2017. Multi channel-kernel canonical correlation analysis for cross-view person re-identification. ACM Transactions on Multimedia Computing, Communications, and Applications 13, 2, Article No. 13. Google Scholar
Digital Library
- Giuseppe Lisanti, Iacopo Masi, Andrew D. Bagdanov, and Alberto Del Bimbo. 2015. Person re-identification by iterative re-weighted sparse ranking. IEEE Transactions on Pattern Analysis and Machine Intelligence 37, 8, 1629--1642.Google Scholar
Digital Library
- Giuseppe Lisanti, Iacopo Masi, and Alberto Del Bimbo. 2014. Matching people across camera views using kernel canonical correlation analysis. In Proceedings of the International Conference on Distributed Smart Cameras. ACM, New York, NY, 10. Google Scholar
Digital Library
- Xiao Liu, Mingli Song, Dacheng Tao, Xingchen Zhou, Chun Chen, and Jiajun Bu. 2014. Semi-supervised coupled dictionary learning for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3550--3557. Google Scholar
Digital Library
- Marco Loog. 2016. Contrastive pessimistic likelihood estimation for semi-supervised classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 38, 3, 462--475. Google Scholar
Digital Library
- Chen Change Loy, Chunxiao Liu, and Shaogang Gong. 2013. Person re-identification by manifold ranking. In Proceedings of the IEEE International Conference on Image Processing. IEEE, Los Alamitos, CA, 3567--3571.Google Scholar
Cross Ref
- Chen Change Loy, Tao Xiang, and Shaogang Gong. 2010. Time-delayed correlation analysis for multi-camera activity understanding. International Journal of Computer Vision 90, 1, 106--129. Google Scholar
Digital Library
- Bingpeng Ma, Yu Su, and Frederic Jurie. 2012. Local descriptors encoded by fisher vectors for person re-identification. In Proceedings of the Workshops of the European Conference on Computer Vision. 413--422. Google Scholar
Digital Library
- Lianyang Ma, Xiaokang Yang, and Dacheng Tao. 2014. Person re-identification over camera networks using multi-task distance metric learning. IEEE Transactions on Image Processing 23, 8, 3656--3670.Google Scholar
Cross Ref
- Tetsu Matsukawa, Takahiro Okabe, Einoshin Suzuki, and Yoichi Sato. 2016. Hierarchical Gaussian descriptor for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1363--1372.Google Scholar
Cross Ref
- Geoffrey J. McLachlan. 1975. Iterative reclassification procedure for constructing an asymptotically optimal rule of allocation in discriminant analysis. Journal of the American Statistical Association 70, 350, 365--369.Google Scholar
Cross Ref
- Alexis Mignon and Frederic Jurie. 2012. PCCA: A new approach for distance learning from sparse pairwise constraints. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2666--2672. Google Scholar
Digital Library
- Sakrapee Paisitkriangkrai, Chunhua Shen, and Anton van den Hengel. 2015. Learning to rank in person re-identification with metric ensembles. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1846--1855.Google Scholar
- Sateesh Pedagadi, James Orwell, Sergio Velastin, and Boghos Boghossian. 2013. Local fisher discriminant analysis for pedestrian re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3318--3325. Google Scholar
Digital Library
- Shibin Qiu and Terran Lane. 2009. A framework for multiple kernel support vector regression and its applications to siRNA efficacy prediction. IEEE/ACM Transactions on Computational Biology and Bioinformatics 6, 2, 190--199. Google Scholar
Digital Library
- Chuck Rosenberg, Martial Hebert, and Henry Schneiderman. 2005. Semi-supervised self-training of object detection models. In Proceedings of the IEEE Workshops on Application of Computer Vision. 29--36. Google Scholar
Digital Library
- Peter M. Roth, Martin Hirzer, Martin Koestinger, Csaba Beleznai, and Horst Bischof. 2014. Mahalanobis Distance Learning for Person Re-identification. Springer, 247--267.Google Scholar
- Ling Shao, Li Liu, and Mengyang Yu. 2016. Kernelized multiview projection for robust action recognition. International Journal of Computer Vision 118, 2, 115--129. Google Scholar
Digital Library
- Yang Shen, Weiyao Lin, Junchi Yan, Mingliang Xu, Jianxin Wu, and Jingdong Wang. 2015. Person re-identification with correspondence structure learning. In Proceedings of the IEEE International Conference on Computer Vision. Google Scholar
Digital Library
- Zhiyuan Shi, Timothy M. Hospedales, and Tao Xiang. 2015. Transferring a semantic representation for person re-identification and search. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
Cross Ref
- Ashish Shrivastava, Vishal M. Patel, and Rama Chellappa. 2014. Multiple kernel learning for sparse representation-based classification. IEEE Transactions on Image Processing 23, 7, 3013--3024.Google Scholar
Cross Ref
- Chi Su, Fan Yang, Shiliang Zhang, Qi Tian, Larry S. Davis, and Wen Gao. 2015. Multi-task learning with low rank attribute embedding for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision. 3739--3747. Google Scholar
Digital Library
- Masashi Sugiyama. 2006. Local fisher discriminant analysis for supervised dimensionality reduction. In Proceedings of the International Conference on Machine Learning. ACM, New York, NY, 905--912. Google Scholar
Digital Library
- Masashi Sugiyama, Tsuyoshi Id, Shinichi Nakajima, and Jun Sese. 2010. Semi-supervised local fisher discriminant analysis for dimensionality reduction. Machine Learning 78, 1--2, 35--61. Google Scholar
Digital Library
- R. Rama Varior, G. Wang, J. Lu, and T. Liu. 2016. Learning invariant color features for person reidentification. IEEE Transactions on Image Processing 25, 7, 3395--3410. Google Scholar
Digital Library
- Fei Xiong, Mengran Gou, Octavia Camps, and Mario Sznaier. 2014. Person re-identification using kernel-based metric learning methods. In Proceedings of the European Conference on Computer Vision. 1--16.Google Scholar
Cross Ref
- Xun Yang, Meng Wang, Luming Zhang, and Dacheng Tao. 2016b. Empirical risk minimization for metric learning using privileged information. In Proceedings of the 25th International Joint Conference on Artificial Intelligence. Google Scholar
Digital Library
- Yang Yang, Zhen Lei, Shifeng Zhang, Hailin Shi, and Stan Z. Li. 2016a. Metric embedded discriminative vocabulary learning for high-level person representation. In Proceedings of the International Joint Conference on Artificial Intelligence. Google Scholar
Digital Library
- Yang Yang, Jimei Yang, Junjie Yan, Shengcai Liao, Dong Yi, and Stan Z. Li. 2014. Salient color names for person re-identification. In Proceedings of the European Conference on Computer Vision. 536--551.Google Scholar
- David Yarowsky. 1995. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics. 189--196. Google Scholar
Digital Library
- Jun Yu, Meng Wang, and Dacheng Tao. 2012. Semisupervised multiview distance metric learning for cartoon synthesis. IEEE Transactions on Image Processing 21, 11, 4636--4648. Google Scholar
Digital Library
- Li Zhang, Tao Xiang, and Shaogang Gong. 2016b. Learning a discriminative null space for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
Cross Ref
- Ying Zhang, Baohua Li, Huchuan Lu, Atshushi Irie, and Xiang Ruan. 2016a. Sample-specific SVM learning for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
Cross Ref
- Yu Zhang and Dit-Yan Yeung. 2012. Transfer metric learning with semi-supervised extension. ACM Transactions on Intelligent Systems and Technology 3, 3, 54. Google Scholar
Digital Library
- Rui Zhao, Wanli Ouyang, and Xiaogang Wang. 2013. Unsupervised salience learning for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3586--3593. Google Scholar
Digital Library
- Rui Zhao, Wanli Ouyang, and Xiaogang Wang. 2014. Learning mid-level filters for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 144--151. Google Scholar
Digital Library
- Liang Zheng, Zhi Bie, Yifan Sun, Jingdong Wang, Chi Su, Shengjin Wang, and Qi Tian. 2016a. MARS: A video benchmark for large-scale person re-identification. In Proceedings of the European Conference on Computer Vision. 868--884.Google Scholar
Cross Ref
- Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. 2015a. Scalable person re-identification: A benchmark. In Proceedings of the IEEE International Conference on Computer Vision. 1116--1124. Google Scholar
Digital Library
- Liang Zheng, Shengjin Wang, Lu Tian, Fei He, Ziqiong Liu, and Qi Tian. 2015b. Query-adaptive late fusion for image search and person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1741--1750.Google Scholar
Cross Ref
- Liang Zheng, Yi Yang, and Alexander G. Hauptmann. 2016b. Person re-identification: Past, present and future. arXiv:1610.02984.Google Scholar
- Liang Zheng, Hengheng Zhang, Shaoyan Sun, Manmohan Chandraker, and Qi Tian. 2017a. Person re-identification in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Google Scholar
Cross Ref
- Wei-Shi Zheng, Shaogang Gong, and Tao Xiang. 2013. Reidentification by relative distance comparison. IEEE Transactions on Pattern Analysis and Machine Intelligence 35, 3, 653--668. Google Scholar
Digital Library
- Zhedong Zheng, Liang Zheng, and Yi Yang. 2017b. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. arXiv:1701.07717.Google Scholar
- Xiaojin Zhu and Andrew B. Goldberg. 2009. Introduction to semi-supervised learning. Synthesis Lectures on Artificial Intelligence and Machine Learning 3, 1, 1--130. Google Scholar
Digital Library
Index Terms
Enhancing Person Re-identification in a Self-Trained Subspace
Recommendations
Self-Training with Selection-by-Rejection
ICDM '12: Proceedings of the 2012 IEEE 12th International Conference on Data MiningPractical machine learning and data mining problems often face shortage of labeled training data. Self-training algorithms are among the earliest attempts of using unlabeled data to enhance learning. Traditional self-training algorithms label unlabeled ...
A novel inductive semi-supervised SVM with graph-based self-training
IScIDE'12: Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data EngineeringIn this paper, a novel inductive support vector machine for semi-supervised learning, named IS3VM, is proposed, which aims to improve SVM by bootstrapping unlabeled data with self-training. The SVM classifier is iteratively refined through the ...
Semi-supervised Region Metric Learning for Person Re-identification
In large-scale camera networks, label information for person re-identification is usually not available under a large amount of cameras due to expensive human labor efforts. Semi-supervised learning could be employed to train a discriminative classifier ...






Comments