More Web Proxy on the site http://driver.im/

research-article

Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification

Authors:

Zhaoxiang Zhang,

Jian ZhangAuthors Info & Claims

IEEE Transactions on Image Processing, Volume 28, Issue 3

Pages 1391 - 1403

https://doi.org/10.1109/TIP.2018.2874715

Published: 01 March 2019 Publication History

Abstract

Sufficient training data normally is required to train deeply learned models. However, due to the expensive manual process for a labeling large number of images (<italic>i.e.</italic>, annotation), the amount of available training data (<italic>i.e.</italic>, real data) is always limited. To produce more data for training a deep network, generative adversarial network can be used to generate artificial sample data (<italic>i.e.</italic>, generated data). However, the generated data usually does not have annotation labels. To solve this problem, in this paper, we propose a virtual label called Multi-pseudo Regularized Label (MpRL) and assign it to the generated data. With MpRL, the generated data will be used as the supplementary of real training data to train a deep neural network in a semi-supervised learning fashion. To build the corresponding relationship between the real data and generated data, MpRL assigns each generated data a proper virtual label which reflects the likelihood of the affiliation of the generated data to pre-defined training classes in the real data domain. Unlike the traditional label which usually is a single integral number, the virtual label proposed in this paper is a set of weight-based values each individual of which is a number in (0,1] called multi-pseudo label and reflects the degree of relation between each generated data to every pre-defined class of real data. A comprehensive evaluation is carried out by adopting two state-of-the-art convolutional neural networks (CNNs) in our experiments to verify the effectiveness of MpRL. Experiments demonstrate that by assigning MpRL to generated data, we can further improve the person re-ID performance on five re-ID datasets, <italic>i.e.</italic>, Market-1501, DukeMTMC-reID, CUHK03, VIPeR, and CUHK01. The proposed method obtains +6.29%, +6.30%, +5.58%, +5.84%, and +3.48% improvements in rank-1 accuracy over a strong CNN baseline on the five datasets, respectively, and outperforms state-of-the-art methods.

References

[1]

I. Goodfellowet al., “Generative adversarial nets,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2014, pp. 2672–2680.

[2]

A. Radford, L. Metz, and S. Chintala, “Unsupervised representation learning with deep convolutional generative adversarial networks,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2016, pp. 1–16.

[3]

M. Arjovsky, S. Chintala, and L. Bottou. (2017). “Wasserstein gan.” [Online]. Available: https://arxiv.org/abs/1701.07875

[4]

I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. C. Courville, “Improved training of wasserstein gans,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2017, pp. 5767–5777.

[5]

Y. Huang, H. Sheng, Y. Zheng, and Z. Xiong, “DeepDiff: Learning deep difference features on human body parts for person re-identification,” Neurocomputing, vol. 241, pp. 191–203, Jun. 2017.

[6]

X. Qian, Y. Fu, Y.-G. Jiang, T. Xiang, and X. Xue, “Multi-scale deep learning architectures for person re-identification,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Jul. 2017, pp. 5399–5408.

[7]

J. Lin, L. Ren, J. Lu, J. Feng, and J. Zhou, “Consistent-aware deep learning for person re-identification in a camera network,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 5771–5780.

[8]

L. Zheng, Y. Yang, and A. G. Hauptmann. (2016). “Person re-identification: Past, present and future.” [Online]. Available: https://arxiv.org/abs/1610.02984

[9]

L. Zheng, H. Zhang, S. Sun, M. Chandraker, Y. Yang, and Q. Tian, “Person re-identification in the wild,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 1–2.

[10]

Z. Zheng, L. Zheng, and Y. Yang, “A discriminatively learned CNN embedding for person reidentification,” ACM Trans. Multimedia Comput. Commun. Appl., vol. 14, no. 1, p. 13, 2016.

[11]

L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian, “Scalable person re-identification: A benchmark,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2015, pp. 1116–1124.

[12]

Z. Zheng, L. Zheng, and Y. Yang, “Unlabeled samples generated by GAN improve the person re-identification baseline in vitro,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 3754–3762.

[13]

W. Li, R. Zhao, T. Xiao, and X. Wang, “DeepReID: Deep filter pairing neural network for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2014, pp. 152–159.

[14]

T. Salimans, I. J. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, “Improved techniques for training GANs,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2016, pp. 2234–2242.

[15]

S. Hong, H. Noh, and B. Han, “Decoupled deep neural network for semi-supervised semantic segmentation,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2015, pp. 1495–1503.

[16]

J. Dai, K. He, and J. Sun, “BoxSup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2015, pp. 1635–1643.

[17]

M. Bauml, M. Tapaswi, and R. Stiefelhagen, “Semi-supervised learning with constraints for person identification in multimedia data,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2013, pp. 3602–3609.

[18]

Y. Luo, D. Tao, B. Geng, C. Xu, and S. J. Maybank, “Manifold regularized multitask learning for semi-supervised multilabel image classification,” IEEE Trans. Image Process., vol. 22, no. 2, pp. 523–536, Feb. 2013.

Digital Library

[19]

R. Johnson and T. Zhang, “Semi-supervised convolutional neural networks for text categorization via region embedding,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2015, pp. 919–927.

[20]

A. Odena. (2016). “Semi-supervised learning with generative adversarial networks.” [Online]. Available: https://arxiv.org/abs/1606.01583

[21]

D.-H. Lee, “Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks,” in Proc. Workshop Challenges Represent. Learn. (ICML), vol. 3, 2013, pp. 1–2.

[22]

S. Gong and T. Xiang, “Person re-identification,” in Visual Analysis of Behaviour. London, U.K.: Springer, 2011, pp. 301–313.

[23]

S. Liao, Y. Hu, X. Zhu, and S. Z. Li, “Person re-identification by local maximal occurrence representation and metric learning,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Dec. 2015, pp. 2197–2206.

[24]

Y. Chen, W. Zheng, and J. Lai, “Mirror representation for modeling view-specific transform in person re-identification,” in Proc. Int. Joint. Conf. Artif. Intell. (IJCAI), 2015, pp. 3402–3408.

[25]

W.-S. Zheng, S. Gong, and T. Xiang, “Person re-identification by probabilistic relative distance comparison,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2011, pp. 649–656.

[26]

S. Liao and S. Z. Li, “Efficient PSD constrained asymmetric metric learning for person re-identification,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2015, pp. 3685–3693.

[27]

Z. Li, S. Chang, F. Liang, T. S. Huang, L. Cao, and J. R. Smith, “Learning locally-adaptive decision functions for person verification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2013, pp. 3610–3617.

[28]

H.-X. Yu, A. Wu, and W.-S. Zheng, “Cross-view asymmetric metric learning for unsupervised person re-identification,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 994–1002.

[29]

P. Zhang, Q. Wu, J. Xu, and J. Zhang, “Long-term person re-identification using true motion from videos,” in Proc. IEEE Winter Conf. Appl. Comput. Vis (WACV), Mar. 2018, pp. 494–502.

[30]

D. Li, X. Chen, Z. Zhang, and K. Huang, “Learning deep context-aware features over body and latent parts for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 384–393.

[31]

M. Geng, Y. Wang, T. Xiang, and Y. Tian. (2016). “Deep transfer learning for person re-identification.” [Online]. Available: https://arxiv.org/abs/1611.05244

[32]

S. Ding, L. Lin, G. Wang, and H. Chao, “Deep feature learning with relative distance comparison for person re-identification,” Pattern Recognit., vol. 48, no. 10, pp. 2993–3003, Oct. 2015.

Digital Library

[33]

D. Cheng, Y. Gong, S. Zhou, J. Wang, and N. Zheng, “Person re-identification by multi-channel parts-based cnn with improved triplet loss function,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 1335–1344.

[34]

W. Chen, X. Chen, J. Zhang, and K. Huang, “Beyond triplet loss: A deep quadruplet network for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 1–8.

[35]

Y. Huang, H. Sheng, and Z. Xiong, “Person re-identification based on hierarchical bipartite graph matching,” in Proc. IEEE Int. Conf. Image. Process. (ICIP), Sep. 2016, pp. 4255–4259.

[36]

S. Bai, X. Bai, and Q. Tian, “Scalable person re-identification on supervised smoothed manifold,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 1–7.

[37]

Z. Zhong, L. Zheng, D. Cao, and S. Li, “Re-ranking person re-identification with k-reciprocal encoding,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 3652–3661.

[38]

J. Garcia, N. Martinel, C. Micheloni, and A. Gardel, “Person re-identification ranking optimisation by discriminant context information analysis,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2015, pp. 1305–1313.

[39]

J. García, N. Martinel, A. Gardel, I. Bravo, G. L. Foresti, and C. Micheloni, “Discriminant context information analysis for post-ranking person re-identification,” IEEE Trans. Image Process., vol. 26, no. 4, pp. 1650–1665, Apr. 2017.

Digital Library

[40]

S. Ali, O. Javed, N. Haering, and T. Kanade, “Interactive retrieval of targets for wide area surveillance,” in Proc. ACM Int. Conf. Multimedia. (ACMMM), 2010, pp. 895–898.

[41]

H. Wang, S. Gong, X. Zhu, and T. Xiang, “Human-in-the-loop person re-identification,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2016, pp. 405–422.

[42]

C. Liu, C. Change Loy, S. Gong, and G. Wang, “Pop: Person re-identification post-rank optimisation,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Dec. 2013, pp. 441–448.

[43]

C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 2818–2826.

[44]

D. Gray and H. Tao, “Viewpoint invariant pedestrian recognition with an ensemble of localized features,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2008, pp. 262–275.

[45]

W. Li, R. Zhao, and X. Wang, “Human reidentification with transferred metric learning,” in Proc. Asian Conf. Comput. Vis. (ACCV), 2012, pp. 31–44.

[46]

P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, “Object detection with discriminatively trained part-based models,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 9, pp. 1627–1645, Sep. 2010.

Digital Library

[47]

E. Ristani, F. Solera, R. Zou, R. Cucchiara, and C. Tomasi, “Performance measures and a data set for multi-target, multi-camera tracking,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2016, pp. 17–35.

[48]

M. Abadiet al., “TensorFlow: A system for large-scale machine learning,” in Proc. OSDI, vol. 16, 2016, pp. 265–283.

[49]

D. Kingma and J. Ba. (2014). “Adam: A method for stochastic optimization.” [Online]. Available: https://arxiv.org/abs/1412.6980

[50]

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2016, pp. 770–778.

[51]

A. Vedaldi and K. Lenc, “MatConvNet: Convolutional neural networks for MATLAB,” in Proc. ACM Int. Conf. Multimedia. (ACMMM), 2015, pp. 689–692.

[52]

R. R. Varior, M. Haloi, and G. Wang, “Gated siamese convolutional neural network architecture for human re-identification,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2016, pp. 791–808.

[53]

F. Wang, W. Zuo, L. Lin, D. Zhang, and L. Zhang, “Joint learning of single-image and cross-image representations for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 1288–1296.

[54]

T. Matsukawa, T. Okabe, E. Suzuki, and Y. Sato, “Hierarchical Gaussian descriptor for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 1363–1372.

[55]

D. Chen, Z. Yuan, B. Chen, and N. Zheng, “Similarity learning with spatial constraints for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 1268–1277.

[56]

L. Zhang, T. Xiang, and S. Gong, “Learning a discriminative null space for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2016, pp. 1239–1248.

[57]

T. Xiao, S. Li, B. Wang, L. Lin, and X. Wang, “Joint detection and identification feature learning for person search,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 3376–3385.

[58]

S. Zhou, J. Wang, J. Wang, Y. Gong, and N. Zheng, “Point to set similarity based deep feature learning for person reidentification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), vol. 6, Jul. 2017, pp. 1–10.

[59]

H. Zhaoet al., “Spindle net: Person re-identification with human body region guided feature decomposition and fusion,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 1077–1085.

[60]

W. Li, X. Zhu, and S. Gong, “Person re-identification by deep joint learning of multi-loss classification,” in Proc. Int. Joint. Conf. Artifi. Intelli. (IJCAI), 2017, pp. 2194–2200.

[61]

Y. Sun, L. Zheng, W. Deng, and S. Wang, “SVDNet for pedestrian retrieval,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 3800–3808.

[62]

C. Su, J. Li, S. Zhang, J. Xing, W. Gao, and Q. Tian, “Pose-driven deep convolutional model for person re-identification,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 3980–3989.

[63]

L. Zhao, X. Li, J. Wang, and Y. Zhuang, “Deeply-learned part-aligned representations for person re-identification,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2017, pp. 3239–3248.

[64]

Y. Chen, X. Zhu, and S. Gong, “Person re-identification by deep learning multi-scale representations,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), Jul. 2017, pp. 2590–2600.

Cited By

Wu JHuang YGao MNiu YYang MGao ZZhao JWooldridge MDy JNatarajan S(2024)Selective and orthogonal feature activation for pedestrian attribute recognitionProceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence10.1609/aaai.v38i6.28419(6039-6047)Online publication date: 20-Feb-2024
https://dl.acm.org/doi/10.1609/aaai.v38i6.28419
Ang ELin SKot A(2024)Diverse Deep Feature Ensemble Learning for Omni-Domain Generalized Person Re-identificationProceedings of the 2024 9th International Conference on Multimedia and Image Processing10.1145/3665026.3665036(64-71)Online publication date: 20-Apr-2024
https://dl.acm.org/doi/10.1145/3665026.3665036
Wu TZhu RWan S(2024)Semantic Map Guided Identity Transfer GAN for Person Re-identificationACM Transactions on Multimedia Computing, Communications, and Applications10.1145/363135520:11(1-20)Online publication date: 12-Sep-2024
https://dl.acm.org/doi/10.1145/3631355
Show More Cited By

Index Terms

Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
  2. Machine learning
    1. Learning paradigms
      1. Supervised learning
    2. Machine learning approaches
      1. Neural networks

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

Recommendations

Multi-granularity Pseudo-label Collaboration for unsupervised person re-identification
Abstract
Unsupervised person re-identification (ReID) aims at training a model through using fully unlabeled training images. Most successful approaches combine clustering-based pseudo-label prediction with ReID model learning and perform the ...
Highlights
- A Multi-granularity Pseudo-label Collaboration (MPC) method is proposed for unsupervised person ReID.
Unsupervised Person Re-Identification via Multi-Label Classification
Abstract
The challenge of unsupervised person re-identification (ReID) lies in learning discriminative features without true labels. Most of previous works predict single-class pseudo labels through clustering. To improve the quality of generated pseudo ...
Learning safe multi-label prediction for weakly labeled data

In this paper we study multi-label learning with weakly labeled data, i.e., labels of training examples are incomplete, which commonly occurs in real applications, e.g., image classification, document categorization. This setting includes, e.g., (i) ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image IEEE Transactions on Image Processing

IEEE Transactions on Image Processing Volume 28, Issue 3

March 2019

438 pages

ISSN:1057-7149

Issue’s Table of Contents

1057-7149 © 2018 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

Publisher

IEEE Press

Publication History

Published: 01 March 2019

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

36
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 26 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Wu JHuang YGao MNiu YYang MGao ZZhao JWooldridge MDy JNatarajan S(2024)Selective and orthogonal feature activation for pedestrian attribute recognitionProceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence10.1609/aaai.v38i6.28419(6039-6047)Online publication date: 20-Feb-2024
https://dl.acm.org/doi/10.1609/aaai.v38i6.28419
Ang ELin SKot A(2024)Diverse Deep Feature Ensemble Learning for Omni-Domain Generalized Person Re-identificationProceedings of the 2024 9th International Conference on Multimedia and Image Processing10.1145/3665026.3665036(64-71)Online publication date: 20-Apr-2024
https://dl.acm.org/doi/10.1145/3665026.3665036
Wu TZhu RWan S(2024)Semantic Map Guided Identity Transfer GAN for Person Re-identificationACM Transactions on Multimedia Computing, Communications, and Applications10.1145/363135520:11(1-20)Online publication date: 12-Sep-2024
https://dl.acm.org/doi/10.1145/3631355
Wu JHuang YGao MGao ZZhao JZhang HZhang A(2024)A Two-Stream Hybrid Convolution-Transformer Network Architecture for Clothing-Change Person Re-IdentificationIEEE Transactions on Multimedia10.1109/TMM.2023.333156926(5326-5339)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TMM.2023.3331569
Huang YWu QZhang ZShan CHuang YZhong YWang L(2024)Meta Clothing Status Calibration for Long-Term Person Re-IdentificationIEEE Transactions on Image Processing10.1109/TIP.2024.337463433(2334-2346)Online publication date: 18-Mar-2024
https://dl.acm.org/doi/10.1109/TIP.2024.3374634
Huang YHuang YZhang ZWu QZhong YWang L(2024)Enhancing Person Re-Identification Performance Through In Vivo LearningIEEE Transactions on Image Processing10.1109/TIP.2023.334176233(639-654)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TIP.2023.3341762
Wang CNing XLi WBai XGao X(2023)3D Person Re-Identification Based on Global Semantic Guidance and Local Feature AggregationIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2023.332871234:6(4698-4712)Online publication date: 30-Oct-2023
https://dl.acm.org/doi/10.1109/TCSVT.2023.3328712
Jin ZXie JWu BShen L(2023)Weakly Supervised Pedestrian Segmentation for Person Re-IdentificationIEEE Transactions on Circuits and Systems for Video Technology10.1109/TCSVT.2022.321047633:3(1349-1362)Online publication date: 1-Mar-2023
https://dl.acm.org/doi/10.1109/TCSVT.2022.3210476
Zhao ZSong RZhang QDuan PZhang Y(2022)JoT-GAN: A Framework for Jointly Training GAN and Person Re-Identification ModelACM Transactions on Multimedia Computing, Communications, and Applications10.1145/349122518:1s(1-18)Online publication date: 25-Jan-2022
https://dl.acm.org/doi/10.1145/3491225
Yao LKusakunniran WWu QXu JZhang J(2022)Recognizing Gaits Across Walking and Running SpeedsACM Transactions on Multimedia Computing, Communications, and Applications10.1145/348871518:3(1-22)Online publication date: 4-Mar-2022
https://dl.acm.org/doi/10.1145/3488715
Show More Cited By

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents