Skip to main content
SpringerLink
Log in

Hierarchical attributes learning for pedestrian re-identification via parallel stochastic gradient descent combined with momentum correction and adaptive learning rate

  • Advances in Parallel and Distributed Computing for Neural Computing
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Convolutional neural networks (CNNs) have obtained high accuracy results for pedestrian re-identification in the past few years. There is always a trade-off between high accuracy and computational time in CNNs. Training CNN is always very difficult as it may take a long time to produce high accuracy results. To overcome this limitation, a novel method parallel stochastic gradient descent (PSGD) is proposed to train a five-hierarchical parallel CNNs that is designed according to pedestrian attributes. Moreover, the momentum correction and adaptive adjustment of learning rate are applied during training process and the time interval for updating parameters is inspected during optimization of parameters selection. The results of this paper prove the effectiveness of proposed PSGD that successfully decreases the training process by five times and surpasses the state-of-the-art methods of pedestrian re-identification in terms of both accuracy and time. The minimum reported running time of the proposed method is 8.7 s which is minimum among all other state-of-the-art methods. These promising results show the efficiency and performance of the proposed model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Flores A, Belongie SJ (2010) Removing pedestrians from google street view images. In: Computer vision and pattern recognition, pp 53–58

  2. Mwakalonge JL, Siuhi S, White J (2015) Distracted walking: examining the extent to pedestrian safety problems. J Traffic Transp Eng 2(5):327–337

    Google Scholar 

  3. Zhang J, Wang N, Zhang L (2018) Multi-shot pedestrian re-identification via sequential decision making. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6781–6789

  4. Bo L, Lai K, Ren X, Fox D (2011) Object recognition with hierarchical kernel descriptors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1729–1736

  5. Latifi A, Foglino M, Tanaka K, Williams P, Lazdunski A (1996) A hierarchical quorum-sensing cascade in pseudomonas aeruginosa links the transcriptional activators lasr and rhir (vsmr) to expression of the stationary-phase sigma factor rpos. Mol Microbiol 21(6):1137–1146

    Article  Google Scholar 

  6. Ali H, Hariharan M, Yaacob S, Adom AH, Zaba SK, Elshaikh M (2016) Facial emotion recognition under partial occlusion using empirical mode decomposition. In: Proceedings of the IEEE international symposium on robotics and manufacturing automation, pp 1–6

  7. Yan Z, Zhang H, Piramuthu R, Jagadeesh V (2015) Hd-cnn: Hierarchical deep convolutional neural networks for large scale visual recognition. In: Proceedings of the IEEE international conference on computer vision, pp 2740–2748

  8. Oghaz MM, Maarof MA, Rohani MF, Zainal A, Shaid SZ (2019) An optimized skin texture model using gray-level co-occurrence matrix. Neural Comput Appl 31:1835–1853

    Article  Google Scholar 

  9. Mosca A, Magoulas GD (2019) Customised ensemble methodologies for deep learning: Boosted Residual Networks and related approaches. Neural Comput Appl 31:1713–1731

    Article  Google Scholar 

  10. Guo J, Gould S (2016) Depth dropout: efficient training of residual convolutional neural networks. In: Proceedings of the international conference on digital image computing: techniques and applications, pp 1–7

  11. Cheng K, Xu F, Tao F, Qi M, Li M (2017) Data-driven pedestrian re-identification based on hierarchical semantic representation. Concurr Comput Pract Exp 9:e4403

    Google Scholar 

  12. Bhinge S, Levin-Schwartz Y, Adal T (2017) Data-driven fusion of multi-camera video sequences: application to abandoned object detection. In: Proceedings of the IEEE international conference on acoustics, speech and signal processing, pp 1697–1701

  13. Su C, Zhang S, Xing J, Gao W, Tian Q (2016) Deep attributes driven multi-camera person re-identification. In: Proceedings of the European conference on computer vision, pp 475–491

  14. Danaci EG, Ikizlercinbis N (2016) Low-level features for visual attribute recognition. Pattern Recognit Lett 84:185–191

    Article  Google Scholar 

  15. Gao M, Ai H, Bai B (2016) A feature fusion strategy for person re-identification In: Proceedings of the international conference on image processing, pp 4274–4278

  16. Cheng K, Hui K, Zhan Y (2017) Sparse representations based distributed attribute learning for person re-identification In: Multimedia tools and applications. Springer, New York, pp 25015–25037

  17. Cheng K, Tan X, Li M (2014) Sparse representations based attribute learning for flower classification. In: Neurocomputing. Elsevier, pp 416–426

  18. Dass J, Sharma M, Hassan E, Ghosh H (2013) A density based method for automatic hairstyle discovery and recognition. In: Proceedings of the national conference on computer vision, pattern recognition, image processing and graphics, pp 1–4

  19. Kang S, Lee D, Yoo CD (2015) Face attribute classification using attribute-aware correlation map and gated convolutional neural networks. In: Proceedings of the international conference on image processing, pp 4922–4926

  20. Lazo-Cortes MS, Carrasco-Ochoa JA, Sanchez-Diaz G (2013) Easy categorization of attributes in decision tables based on basic binary discernibility matrix. In: Iberoamerican congress on pattern recognition. Springer, New York, pp 302–310

  21. Nguyen TP, Manzanera A, Kropatsch WG (2014) Impact of topology-related attributes from local binary patterns on texture classification. In: Proceedings of the European conference on computer vision, pp 80–93

  22. Liu Y, Yang J, Huang Y, Xu L, Li S, Qi M (2015) Mapreduce based parallel neural networks in enabling large scale machine learning. Comput Intell Neurosci 2015:297672–297672

    Google Scholar 

  23. Vedaldi A, Lenc K (2014) Matconvnet: convolutional neural networks for matlab. In: Proceedings of the 23rd ACM international conference on multimedia, pp 689–692

  24. Xiao G, Li K, Li K, Xu Z (2015) Efficient top-(k, l) top range query processing for uncertain data based on multicore architectures. Distrib Parallel Databases 33(3):381–413

    Article  Google Scholar 

  25. Rafegas I, Vanrell M (2017) Color representation in cnns: parallelisms with biological vision. In: Proceedings of the IEEE international conference on computer vision workshop, pp 2697–2705

  26. Song L, Wang Y, Han Y, Zhao X, Liu B, Li X (2016) C-brain: a deep learning accelerator that tames the diversity of cnns through adaptive data-level parallelization. In: Proceedings of the design automation conference, p 123

  27. Chen J, Li K, Bilal K, Zhou X, Li K, Yu PS (2019) A bi-layered parallel training architecture for large-scale convolutional neural networks. In: IEEE, transactions on parallel and distributed systems, pp 965–976

  28. Li K, Tang X, Veeravalli B, Li K (2015) Scheduling precedence constrained stochastic tasks on heterogeneous cluster systems. IEEE Trans Comput 64(1):191–204

    Article  MathSciNet  MATH  Google Scholar 

  29. Li K, Yang W, Li K (2015) Performance analysis and optimization for SpMV on GPU using probabilistic modeling. IEEE Trans Parallel Distrib Syst 26(1):196–205

    Article  MathSciNet  Google Scholar 

  30. Chen J, Li K, Deng Q, Li K (2019) Distributed deep learning model for intelligent video surveillance systems with edge computing. In: IEEE, transactions on industrial informatics, p 1

  31. Huanzhou Z, Zhuoer G, Haiming Z, Keyang C, Chang-Tsun L, Ligang H (2018) Developing a pattern discovery method in time series data and its GPU acceleration. In: TUP, Big data mining and analytics, pp 266–283

  32. Loshchilov I, Hutter F (2016) Sgdr: stochastic gradient descent with restarts. In: Proceedings of the international conference on learning representations

  33. Wang L, Yang Y, Min MR, Chakradhar ST (2017) Accelerating deep neural network training with inconsistent stochastic gradient descent. In: Neural networks the official journal of the international neural network society. Elsevier, pp 219–229

  34. Sutskever I, Martens J, Dahl GE, Hinton GE (2013) On the importance of initialization and momentum in deep learning. In: Proceedings of the international conference on machine learning, pp 1139–1147

  35. Fan Q, Wu W, Zurada JM (2016) Convergence of batch gradient learning with smoothing regularization and adaptive momentum for neural networks. SpringerPlus 5(1):295

    Article  Google Scholar 

  36. Botev A, Lever G, Barber D (2016) Nesterov’s accelerated gradient and momentum as approximations to regularised update descent In: Proceedings of the international joint conference on neural network, pp 1899–1903

  37. Hadgu AT, Nigam A, Diaz-Aviles E (2015) Large-scale learning with adagrad on spark. In: Proceedings of the IEEE international conference on Big Data, pp 2828–2830

  38. Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: Proceedings of the international conference on learning representations

  39. Li Y, Tong G, Li X, Wang Y, Zou B, Liu Y (2019) PARNet: a joint loss function and dynamic weights network for pedestrian semantic attributes recognition of smart surveillance image. In: Multidisciplinary digital publishing institute, applied sciences, p 2027

  40. Hajj Nadine, Awad Mariette (2019) A piecewise weight update rule for a supervised training of cortical algorithms. Neural Comput Appl 31:1915–1930

    Article  Google Scholar 

  41. Chatzipavlis A, Tsekouras GE, Trygonis V, Velegrakis AF, Tsimikas J, Rigos A, Salmas C (2019) Modeling beach realignment using a neuro-fuzzy network optimized by a novel backtracking search algorithm. Neural Comput Appl 31:1747–1763

    Article  Google Scholar 

  42. Chen Y, Duffner S, Stoian A, Dufour J, Baskurt A (2018) Pedestrian attribute recognition with part-based CNN and combined feature representations. In: Proceedings of the international joint conference on computer vision imaging and computer graphics theory and applications, pp 114–122

  43. Li D, Chen X, Zhang Z, Huang K (2018) Pose guided deep model for pedestrian attribute recognition in surveillance scenarios. In: Proceedings of the IEEE international conference on multimedia and expo (ICME), pp 1–6

  44. Chen Z, Li A, Wang Y (2019) Video-Based Pedestrian Attribute Recognition In: Computer vision and pattern recognition. arXiv:1901.05742

  45. Cai L, Zhu J, Zeng H, Chen J, Cai C, Ma K (2018) Hog-assisted deep feature learning for pedestrian gender recognition. J Frank Inst 355:1991–2008

    Article  Google Scholar 

  46. Wang X, Zheng S, Yang R, Luo B, Tang J (2019) Pedestrian attribute recognition: a survey. In: Computer vision and pattern recognition. arXiv:1901.07474

  47. Li D, Zhang Z, Chen X, Ling H, Huang K (2016) A richly annotated dataset for pedestrian attribute recognition. In: Computer vision and pattern recognition. arXiv:1603.07054

  48. Bottou Leon (2012) Stochastic gradient descent tricks. In: Neural networks: tricks of the trade. Springer, New York, pp 421–436

  49. Dong X, Tsong Y, Shen M (2014) Equivalence tests for interchangeability based on two one-sided probabilities. J Biopharm Stat 24(6):1332–1348

    Article  MathSciNet  Google Scholar 

  50. Gray D, Brennan S, Tao H (2007) Evaluating appearance models for recognition, reacquisition, and tracking. In: Proceedings of the IEEE international workshop on performance evaluation for tracking and surveillance, vol 3(5), pp 501–512

  51. Li W, Wang X (2013) Locally aligned feature transforms across views. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3594–3601

  52. Li W, Zhao R, Wang X (2012) Human reidentification with transferred metric learning. In: Asian conference on computer vision. Springer, New York, pp 31–44

  53. Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: Proceedings of the European conference on computer vision workshops, pp 17–35

  54. Hoang VD, Le MH, Jo KH (2014) Hybrid cascade boosting machine using variant scale blocks based hog features for pedestrian detection. Neurocomputing 135(C):357–366

    Article  Google Scholar 

  55. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of the international conference on learning representations

  56. Jung H, Choi MK, Jung J, Lee JH, Kwon S, Jung WY (2017) Resnet-based vehicle classification and localization in traffic surveillance systems. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 934–940

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

  58. Chollet François (2017) Xception: Deep learning with depthwise separable convolutions In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1251–1258

  59. Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \(< 0.5\) MB model size. In: Computer vision and pattern recognition. arXiv:1602.07360

  60. Layne R, Hospedales TM, Gong S (2014) Attributes-based re-identification. Springer, London (Person Re-Identification)

  61. Roth PM, Hirzer M, Kostinger M, Beleznai C, Bischof H (2014) Mahalanobis distance learning for person re-identification. In: Springer, London (Person Re-Identification), pp 247–267

  62. Farenzena M, Bazzani L, Perina A, Murino V, Cristani M (2010) Person re-identification by symmetry-driven accumulation of local features. In: Computer vision and pattern recognition, pp 2360–2367

  63. Layne R, Hospedales TM, Gong S (2012) Person re-identification by attributes. In: British machine vision conference, pp 1–11

  64. Umeda T, Sun Y, Irie G, Sudo K, Kinebuchi T (2016) Attribute discovery for person re-identification. In: International conference on multimedia modeling. Springer, New York, pp 268–276

  65. Zhao R, Ouyang W, Wang X (2013) Unsupervised salience learning for person re-identification. In: Proceedings of the ieee conference on computer vision and pattern recognition, pp 3586–3593

Download references

Acknowledgements

This research is supported by National Natural Science Foundation of China (61972183, 61602215, 61672268) and the Director Foundation Project of National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data (PSRPC).

Author information

Authors and Affiliations

  1. School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, China

    Keyang Cheng, Fei Tao & Yongzhao Zhan

  2. National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data, Beijing, China

    Keyang Cheng

  3. Department of Electronic and Computer Engineering, Brunel University, London, UK

    Maozhen Li

  4. The Key Laboratory of Embedded Systems and Service Computing, Tongji University, Shanghai, China

    Maozhen Li

  5. College of Information Science and Engineering, Hunan University, Changsha, China

    Kenli Li

Authors
  1. Keyang Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fei Tao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yongzhao Zhan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Maozhen Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kenli Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Keyang Cheng.

Ethics declarations

Conflict of interest

We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cheng, K., Tao, F., Zhan, Y. et al. Hierarchical attributes learning for pedestrian re-identification via parallel stochastic gradient descent combined with momentum correction and adaptive learning rate. Neural Comput & Applic 32, 5695–5712 (2020). https://doi.org/10.1007/s00521-019-04485-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-019-04485-2

Keywords

Search

Navigation