research-article

Unsupervised person re-identification via re-ranking enhanced sample-specific metric learning

Authors:

Fei QinAuthors Info & Claims

2017 IEEE International Conference on Image Processing (ICIP)

Pages 3405 - 3409

https://doi.org/10.1109/ICIP.2017.8296914

Published: 17 September 2017 Publication History

Abstract

Despite of the great progress of image-based person re-identification, most existing methods use supervised metric learning to build re-identification models and thus require repeated human effort to annotate sample pairs from non-overlapping cameras. In this paper, we propose an unsupervised sample-specific metric learning approach (SSML) to alleviate this problem. Specifically, using samples those are negatives (with a high probability) to the query samples, we train a local metric for each query sample following the max-margin learning theory. Moreover, a KNN intersection re-ranking (KIRR) method is used to further decrease the ambiguity of samples and aggregate the re-identification performance. With experiments on three widely used person re-identification datasets: VIPeR, CUHK01, and PRID, we demonstrate that the proposed approach is simple but effective.

6. References

[1]

Douglas Gray and Hai Tao, “Viewpoint invariant pedestrian recognition with an ensemble of localized features,” in ECCV. 2008, pp. 262–275, Springer.

Digital Library

[2]

Michela Farenzena, Loris Bazzani, Alessandro Peri-na, Vittorio Murino, and Marco Cristani, “Person reidentification by symmetry-driven accumulation of local features,” in CVPR. IEEE, 2010, pp. 2360–2367.

[3]

Bingpeng Ma, Yu Su, and Frédéric Jurie, “Local descriptors encoded by fisher vectors for person reidentification,” in ECCV, Workshops and Demonstrations. Springer, 2012, pp. 413–422.

[4]

Rui Zhao, Wanli Ouyang, and Xiaogang Wang, “Learning mid-level filters for person re-identification,” in CVPR. IEEE, 2014, pp. 144–151.

Digital Library

[5]

Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z Li, “Person re-identification by local maximal occurrence representation and metric learning,” in CVPR, 2015, pp. 2197–2206.

[6]

Tetsu Matsukawa, Takahiro Okabe, Einoshin Suzuki, and Yoichi Sato, “Hierarchical gaussian descriptor for person re-identification,” in CVPR, 2016, pp. 1363–1372.

[7]

Martin Koestinger, Martin Hirzer, Paul Wohlhart, Peter M Roth, and Horst Bischof, “Large scale metric learning from equivalence constraints,” in CVPR. IEEE, 2012, pp. 2288–2295.

Digital Library

[8]

Wei-Shi Zheng, Shaogang Gong, and Tao Xiang, “Rei-dentification by relative distance comparison,” PAMI, IEEE Transactions on, vol. 35, no. 3, pp. 653–668, 2013.

Digital Library

[9]

Fei Xiong, Mengran Gou, Octavia Camps, and Mario Sznaier, “Person re-identification using kernel-based metric learning methods,” in ECCV. 2014, pp. 1–16, Springer.

[10]

Giuseppe Lisanti, Iacopo Masi, and Alberto Del Bim-bo, “Matching people across camera views using kernel canonical correlation analysis,” in ICDSC. ACM, 2014, p. 10.

[11]

Martin Hirzer, Peter M Roth, Martin Kostinger, and Horst Bischof, “Relaxed pairwise learned metric for person re-identification,” in ECCV. 2012, pp. 780–793, Springer.

Digital Library

[12]

Yang Yang, Jimei Yang, Junjie Yan, Shengcai Liao, Dong Yi, and Stan Z Li, “Salient color names for person re-identification,” in ECCV. 2014, pp. 536–551, Springer.

[13]

Li Zhang, Tao Xiang, and Shaogang Gong, “Learning a discriminative null space for person re-identification,” in CVPR, 2016, pp. 1239–1248.

[14]

Giuseppe Lisanti, Iacopo Masi, Andrew D Bagdanov, and Alberto Del Bimbo, “Person re-identification by iterative re-weighted sparse ranking,” PAMI, IEEE transactions on, vol. 37, no. 8, pp. 1629–1642, 2015.

Digital Library

[15]

Hanxiao Wang, Shaogang Gong, and Tao Xiang, “Unsupervised learning of generative topic saliency for person re-identification,” in BMVC, 2014.

[16]

Elyor Kodirov, Tao Xiang, and Shaogang Gong, “Dictionary learning with iterative laplacian regularisation for unsupervised person re-identification,” in BMVC, 2015, vol. 3, p. 8.

[17]

Peixi Peng, Tao Xiang, Yaowei Wang, Massimiliano Pontil, Shaogang Gong, Tiejun Huang, and Yonghong Tian, “Unsupervised cross-dataset transfer learning for person re-identification,” in CVPR, 2016, pp. 1306–1315.

[18]

Ethan Fetaya and Shimon Ullman, “Learning local invariant mahalanobis distances,” in ICML, 2015, pp. 162–168.

[19]

Pedro F Felzenszwalb, Ross B Girshick, David McAllester, and Deva Ramanan, “Object detection with discriminatively trained part-based models,” PAMI, IEEE Transactions on, vol. 32, no. 9, pp. 1627–1645, 2010.

Digital Library

[20]

Douglas Gray, Shane Brennan, and Hai Tao, “Evalu-ating appearance models for recognition, reacquisition, and tracking,” in PETS. Citeseer, 2007, vol. 3.

[21]

Wei Li, Rui Zhao, and Xiaogang Wang, “Human reidentification with transferred metric learning,” in ACCV, 2012, pp. 31–44.

Digital Library

[22]

Martin Hirzer, Csaba Beleznai, Peter M Roth, and Horst Bischof, “Person re-identification by descriptive and discriminative classification,” in Scandinavian conference on Image analysis. Springer, 2011, pp. 91–102.

[23]

Navneet Dalal and Bill Triggs, “Histograms of oriented gradients for human detection,” in CVPR. IEEE, 2005, vol. 1, pp. 886–893.

Digital Library

[24]

Timo Ahonen, Abdenour Hadid, and Matti Pietikainen, “Face description with local binary patterns: Application to face recognition,” PAMI, IEEE transactions on, vol. 28, no. 12, pp. 2037–2041, 2006.

Digital Library

Cited By

Chang JChang J(2020)Improving Retrieval Efficiency of Person Re-Identification Based on Resnet50Proceedings of the 6th International Conference on Frontiers of Educational Technologies10.1145/3404709.3404773(98-102)Online publication date: 5-Jun-2020
https://dl.acm.org/doi/10.1145/3404709.3404773

Index Terms

Unsupervised person re-identification via re-ranking enhanced sample-specific metric learning
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
  2. Machine learning
    1. Learning paradigms
2. Information systems

Index terms have been assigned to the content through auto-classification.

Recommendations

Unsupervised metric learning for person re-identification by image re-ranking

Person re-identification is an important and challenging problem in video surveillance. Most of the methods are based on supervised distance metrics learning, which have to label samples for distance metrics learning, while it is hardly done in massive ...
Disentangled Sample Guidance Learning for Unsupervised Person Re-Identification
Unsupervised person re-identification (Re-ID) is challenging due to the lack of ground truth labels. Most existing methods employ iterative clustering to generate pseudo labels for unlabeled training data to guide the learning process. However, how to ...
Regularized local metric learning for person re-identification

We have proposed a new metric learning approach by exploiting both global and local information of samples to learn similarity for person re-identification.We have presented a regularization approach to address the small sample size problem in previous ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

2017 IEEE International Conference on Image Processing (ICIP)

Sep 2017

4869 pages

Copyright © 2017.

Publisher

IEEE Press

Publication History

Published: 17 September 2017

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 12 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Chang JChang J(2020)Improving Retrieval Efficiency of Person Re-Identification Based on Resnet50Proceedings of the 6th International Conference on Frontiers of Educational Technologies10.1145/3404709.3404773(98-102)Online publication date: 5-Jun-2020
https://dl.acm.org/doi/10.1145/3404709.3404773

View Options

View options

Figures

Tables

Media

View Table of Conten