article

Person re-identification by the asymmetric triplet and identification loss function

Authors:

Shizhou ZhangAuthors Info & Claims

Multimedia Tools and Applications, Volume 77, Issue 3

Pages 3533 - 3550

https://doi.org/10.1007/s11042-017-5182-z

Published: 01 February 2018 Publication History

Abstract

Person re-identification(re-id) aims to match the same individuals across different non-overlapping camera views. In this paper, we analyze the effectiveness of two widely used triplet loss and softmax loss on person re-id task. We conclude that the triplet loss function is suitable for the relatively small datasets with the shallow neural network, while the softmax loss works better on larger datasts with relatively deeper network architecture. Both of them are essential to the person re-id task. Moreover, we present a convolutional neural network (CNN) model under the joint supervision of the triplet loss and softmax loss for person re-id. This method can get a slightly better performance than either of them. The triplet loss makes the distance of the same individual's images closer, and pushes the instances of different individuals far apart from each other, which can effectively reduce the intra-personal variations. Meanwhile, the person identification cost, which is implemented by the softmax loss with the "center loss" embedded, can discriminatively learn some identity-related feature representations (i.e. features with large inter-personal variations). Extensive experimental results demonstrate the effectiveness of our proposed method, and we have obtained promising performance on the challenging i-LIDS, PRID2011 and CUHK03 datasets.

References

[1]

Ahmed E, Jones M, Marks TK (2015) An improved deep learning architecture for person re-identification. CVPR 5:25

[2]

Bak S, Corvee E, Brémond F, Thonnat M (2010) Person re-identification using spatial covariance regions of human body parts. In: Seventh IEEE international conference on advanced video and signal based surveillance (AVSS), 2010, pp 435---440

Digital Library

[3]

Chang X, Yang Y (2016) Semi-supervised feature analysis by mining correlations among multiple tasks. IEEE Trans Neural Netw Learn Syst.

[4]

Chang X, Nie F, Wang S, Yang Y, Zhou X, Zhang C (2016) Compound rank-k projections for bilinear analysis. IEEE Trans Neural Netw Learn Syst 27(7):1502---1513

[5]

Chang X, Ma Z, Lin M, Yang Y, Hauptmann A (2017) Feature interaction augmented sparse learning for fast kinect motion detection. IEEE Trans Image Process 26(5):3911---3920

[6]

Chang X, Ma Z, Yang Y, Zeng Z, Hauptmann AG (2017) Bi-level semantic representation analysis for multimedia event detection. IEEE Transactions on Cybernetics 47(5):1180---1197

[7]

Chang X, Yu Y-L, Yang Y, Xing EP (2017) Semantic pooling for complex event analysis in untrimmed videos. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(8):1617---1632

Digital Library

[8]

Cheng DS, Cristani M, Stoppa M, Bazzani L, Murino V (2011) Custom pictorial structures for re-identification. In: BMVC, vol 1, p 6

[9]

Cheng D, Chang X, Liu L, Hauptmann AG, Gong Y, Zheng N (2017) Discriminative dictionary learning with ranking metric embedded for person re-identification. In: IJCAI, pp 964---970

Digital Library

[10]

Davis JV, Kulis B, Jain P, Sra S, Dhillon IS (2007) Information-theoretic metric learning. In: ICML, pp 209---216

Digital Library

[11]

Ding S, Lin L, Wang G et al (2015) Deep feature learning with relative distance comparison for person re identification. Pattern Recogn 48(10):2993---3003

Digital Library

[12]

Dollár P, Tu Z, Tao H, Belongie S (2007) Feature mining for image classification. In: CVPR, pp 1---8

[13]

Farenzena M, Bazzani L, Perina A, Murino V, Cristani M (2010) Person re-identification by symmetry-driven accumulation of local features. In: CVPR, pp 2360---2367

[14]

Gheissari N, Sebastian TB, Hartley R (2006) Person reidentification using spatiotemporal appearance. In: CVPR, vol 2, pp 1528---1535

Digital Library

[15]

Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp 580---587

Digital Library

[16]

Globerson A, Roweis ST (2005) Metric learning by collapsing classes. In: NIPS, pp 451---458

Digital Library

[17]

Gray D, Tao H (2008) Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: ECCV, pp 262---275

Digital Library

[18]

Guillaumin M, Verbeek J, Schmid C (2009) Is that you? Metric learning approaches for face identification. In: CVPR, pp 498---505

[19]

Hirzer M, Beleznai C, Roth PM, Bischof H (2011) Person re-identification by descriptive and discriminative classification. In: Image analysis, pp 91---102

Digital Library

[20]

Hirzer M, Roth PM, Bischof H (2012) Person re-identification by efficient impostor-based metric learning. In: IEEE ninth international conference on advanced video and signal-based surveillance (AVSS), 2012, pp 203---208

Digital Library

[21]

Hu W, Hu M, Zhou X, Tan T, Lou J, Maybank S (2006) Principal axis-based correspondence between multiple cameras for people tracking. IEEE Trans Pattern Anal Mach Intell 28(4):663--- 671

Digital Library

[22]

Khamis S, Kuo C-H, Singh VK, Shet VD, Davis LS (2014) Joint learning for attribute-consistent person re-identification. In: ECCV, pp 134---146

[23]

Koestinger M, Hirzer M, Wohlhart P, Roth PM, Bischof H (2012) Large scale metric learning from equivalence constraints. In: CVPR, pp 2288---2295

Digital Library

[24]

Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: NIPS, pp 1097---1105

Digital Library

[25]

Li W, Wang X (2013) Locally aligned feature transforms across views. In: CVPR, pp 3594---3601

Digital Library

[26]

Li Z, Chang S, Liang F, Huang TS, Cao L, Smith JR (2013) Learning locally-adaptive decision functions for person verification. In: CVPR, pp 3610---3617

Digital Library

[27]

Li W, Zhao R, Xiao T, Wang X (2014) Deepreid: deep filter pairing neural network for person re-identification. In: CVPR, pp 152---159

Digital Library

[28]

Ma B, Su Y, Jurie F (2012) Bicov: a novel image representation for person re-identification and face verification. In: BMVC, p 11

[29]

McLaughlin N, Martinez del Rincon J, Miller P (2016) Recurrent convolutional network for video-based person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1325---1334

[30]

Paisitkriangkrai S, Shen C, van den Hengel A Learning to rank in person re-identification with metric ensembles. arXiv:1503.01543

[31]

Park U, Jain AK, Kitahara I, Kogure K, Hagita N (2006) Vise: visual search engine using multiple networked cameras. In: ICPR, vol 3, pp 1204---1207

Digital Library

[32]

Roth PM, Hirzer M, Köstinger M, Beleznai C, Bischof H (2014) Mahalanobis distance learning for person re-identification. In: Person re-identification, pp 247---267

[33]

Schroff F, Kalenichenko D, Philbin J Facenet: a unified embedding for face recognition and clustering. arXiv:1503.03832

[34]

Schwartz WR, Davis LS (2009) Learning discriminative appearance-based models using partial least squares. In: XXII Brazilian symposium on computer graphics and image processing (SIBGRAPI), 2009, pp 322---329

Digital Library

[35]

Sun Y, Chen Y, Wang X, Tang X (2014) Deep learning face representation by joint identification-verification. In: NIPS, pp 1988---1996

Digital Library

[36]

Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1---9

[37]

UK (2008) Home office i-lids multiple camera tracking scenario definition

[38]

Varior RR, Haloi M, Wang G (2016) Gated siamese convolutional neural network architecture for human re-identification. In: European conference on computer vision. Springer, pp 791---808

[39]

Wang X, Doretto G, Sebastian T, Rittscher J, Tu P (2007) Shape and appearance context modeling. In: ICCV, pp 1---8

[40]

Wang J, Song Y, Leung T, Rosenberg C, Wang J, Philbin J, Chen B, Wu Y (2014) Learning fine-grained image similarity with deep ranking. In: CVPR, pp 1386---1393

Digital Library

[41]

Weinberger KQ, Blitzer J, Saul LK (2005) Distance metric learning for large margin nearest neighbor classification. In: NIPS, pp 1473---1480

Digital Library

[42]

Wen Y, Zhang K, Li Z, Qiao Y (2016) A discriminative feature learning approach for deep face recognition. In: European conference on computer vision. Springer, pp 499---515

[43]

Xiao Q, Cao K, Chen H, Peng F, Zhang C Cross domain knowledge transfer for person re-identification. arXiv:1611.06026

[44]

Xiao T, Li H, Ouyang W, Wang X (2016) Learning deep feature representations with domain guided dropout for person re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1249---1258

[45]

Xing EP, Jordan MI, Russell S, Ng AY (2002) Distance metric learning with application to clustering with side-information. In: NIPS, pp 505---512

Digital Library

[46]

Xiong F, Gou M, Camps O, Sznaier M (2014) Person re-identification using kernel-based metric learning methods. In: ECCV, pp 1---16

[47]

Yan Y, Ni B, Song Z, Ma C, Yan Y, Yang X (2016) Person re-identification via recurrent feature aggregation. In: European conference on computer vision. Springer, pp 701---716

[48]

Yang Y, Yang J, Yan J, Liao S, Yi D, Li SZ (2014) Salient color names for person re-identification. In: ECCV, pp 536---551

[49]

Yi D, Lei Z, Liao S, Li SZ (2014) Deep metric learning for person re-identification. In: ICPR, pp 34---39

Digital Library

[50]

Zhang D, Han J, Han J, Shao L (2016) Cosaliency detection based on intrasaliency prior transfer and deep intersaliency mining. IEEE Transactions on Neural Networks and Learning Systems 27(6):1163---1176

[51]

Zhang D, Han J, Li C, Wang J, Li X (2016) Detection of co-salient objects by looking deep and wide. Int J Comput Vis 120(2):215---232

Digital Library

[52]

Zhao R, Ouyang W, Wang X (2013) Person re-identification by salience matching. In: ICCV, pp 2528---2535

Digital Library

[53]

Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. In: CVPR, pp 3586---3593

Digital Library

[54]

Zhao R, Ouyang W, Wang X (2014) Learning mid-level filters for person re-identification. In: CVPR, pp 144---151

Digital Library

[55]

Zheng W-S, Gong S, Xiang T (2011) Person re-identification by probabilistic relative distance comparison. In: CVPR, pp 649---656

Digital Library

[56]

Zheng Z, Zheng L, Yang Y A discriminatively learned cnn embedding for person re-identification. arXiv:1611.05666

[57]

Zhu L, Shen J, Jin H, Xie L, Zheng R (2015) Landmark classification with hierarchical multi-modal exemplar feature. IEEE Trans Multimedia 17(7):981---993

Digital Library

[58]

Zhu L, Shen J, Liu X et al (2016) Learning compact visual representation with canonical views for robust mobile landmark search. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence. AAAI Press, pp 3959---3965

Digital Library

[59]

Zhu L, Shen J, Xie L et al (2016) Unsupervised topic hypergraph hashing for efficient mobile image retrieval. IEEE Trans Cybern

Cited By

Hong XZhang LYu XXie WXie Y(2024)MBA-Net: multi-branch attention network for occluded person re-identificationMultimedia Tools and Applications10.1007/s11042-023-15312-183:2(6393-6412)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1007/s11042-023-15312-1
Liu MZhao JZhou YZhu HYao RChen Y(2022)Survey for person re-identification based on coarse-to-fine feature learningMultimedia Tools and Applications10.1007/s11042-022-12510-181:15(21939-21973)Online publication date: 1-Jun-2022
https://dl.acm.org/doi/10.1007/s11042-022-12510-1
Zou GFu GPeng XLiu YGao MLiu Z(2021)Person re-identification based on metric learning: a surveyMultimedia Tools and Applications10.1007/s11042-021-10953-680:17(26855-26888)Online publication date: 1-Jul-2021
https://dl.acm.org/doi/10.1007/s11042-021-10953-6
Show More Cited By

Recommendations

Deep feature embedding learning for person re-identification based on lifted structured loss

Person re-identification (re-id) aims at matching the same individual in videos captured by multiple cameras, and much progress has been made in recent years due to large scale pedestrian data sets and deep learning-based techniques. In this paper, we ...
A loss combination based deep model for person re-identification

The Convolutional Neural Network (CNN) has significantly improved the state-of-the-art in person re-identification (re-ID). In the existing available identification CNN model, the softmax loss function is employed as the supervision signal to train the ...
Triplet Ratio Loss for Robust Person Re-identification
Pattern Recognition and Computer Vision
Abstract
Triplet loss has been proven to be useful in the task of person re-identification (ReID). However, it has limitations due to the influence of large intra-pair variations and unreasonable gradients. In this paper, we propose a novel loss to reduce ...

Comments

Information & Contributors

Information

Published In

cover image Multimedia Tools and Applications

Multimedia Tools and Applications Volume 77, Issue 3

February 2018

1114 pages

ISSN:1380-7501

Issue’s Table of Contents

Copyright © Copyright © 2018 Springer Science+Business Media, LLC, part of Springer Nature.

Publisher

Kluwer Academic Publishers

United States

Publication History

Published: 01 February 2018

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 21 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Hong XZhang LYu XXie WXie Y(2024)MBA-Net: multi-branch attention network for occluded person re-identificationMultimedia Tools and Applications10.1007/s11042-023-15312-183:2(6393-6412)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1007/s11042-023-15312-1
Liu MZhao JZhou YZhu HYao RChen Y(2022)Survey for person re-identification based on coarse-to-fine feature learningMultimedia Tools and Applications10.1007/s11042-022-12510-181:15(21939-21973)Online publication date: 1-Jun-2022
https://dl.acm.org/doi/10.1007/s11042-022-12510-1
Zou GFu GPeng XLiu YGao MLiu Z(2021)Person re-identification based on metric learning: a surveyMultimedia Tools and Applications10.1007/s11042-021-10953-680:17(26855-26888)Online publication date: 1-Jul-2021
https://dl.acm.org/doi/10.1007/s11042-021-10953-6
Zhu XLi YSun JChen HZhu J(2021)Unsupervised domain adaptive person re-identification via camera penalty learningMultimedia Tools and Applications10.1007/s11042-021-10589-680:10(15215-15232)Online publication date: 1-Apr-2021
https://dl.acm.org/doi/10.1007/s11042-021-10589-6
Deng XLiao KZheng YLin GLei H(2021)A deep multi-feature distance metric learning method for pedestrian re-identificationMultimedia Tools and Applications10.1007/s11042-020-10458-880:15(23113-23131)Online publication date: 1-Jun-2021
https://dl.acm.org/doi/10.1007/s11042-020-10458-8
Zhang YLiu SQi LColeman SKerr DShi W(2020)Multi-level and multi-scale horizontal pooling network for person re-identificationMultimedia Tools and Applications10.1007/s11042-020-09427-y79:39-40(28603-28619)Online publication date: 5-Aug-2020
https://dl.acm.org/doi/10.1007/s11042-020-09427-y

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents