Skip to main content
SpringerLink
Log in

Self-paced hierarchical metric learning (SPHML)

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Metric learning aims to learn a distance to measure the difference between two samples, and it plays an important role in pattern recognition tasks. Most of the existing metric learning methods rely on pairs of samples. However, the importance of sample pairs varies greatly because of possible noise and the difference between samples and the decision boundaries. In this paper, we propose a robust hierarchical metric learning (SPHML) framework based on self-paced learning, which can help gain knowledge about the weights of sample pairs and utilize them in an easy or hard manner. Hierarchical nonlinear functions are learned by back-propagation to map sample pairs into a more discriminative feature space. Experimentally, our method achieves very competitive performance when compared with state-of-the-art methods.

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

Similar content being viewed by others

Notes

  1. http://vis-www.cs.umass.edu/lfw/results.html.

  2. https://www.cs.tau.ac.il/~wolf/ytfaces/.

References

  1. Basu S, Christensen J (2013) Teaching classification boundaries to humans. In: Twenty-seventh AAAI conference on artificial intelligence

  2. Bengio Y, Louradour J, Collobert R, Weston J (2009) Curriculum learning. In: Proceedings of the 26th annual international conference on machine learning, ICML 2009, Montreal, Quebec, Canada, June 14–18, 2009

  3. Cai X, Wang C, Xiao B, Xue C, Ji Z (2012) Deep nonlinear metric learning with independent subspace analysis for face verification. In: ACM international conference on multimedia

  4. Cevikalp H, Triggs B (2010) Face recognition based on image sets. In: Computer vision & pattern recognition

  5. Chatzis S (2014) Dynamic Bayesian probabilistic matrix factorization. In: Twenty-eighth AAAI conference on artificial intelligence

  6. Davis JV, Kulis B, Jain P, Sra S, Dhillon IS (2007) Information-theoretic metric learning. In: ICML 07: international conference on machine learning

  7. Dong Y, Zhen L, Li SZ (2013) Towards pose robust face recognition. In: Computer vision & pattern recognition

  8. Guillaumin M, Verbeek JJ, Schmid C (2009) Is that you? Metric learning approaches for face identification. In: IEEE international conference on computer vision

  9. Guo H, Zhu K, Tang M, Wang J (2019) Two-level attention network with multi-grain ranking loss for vehicle re-identification. IEEE Trans Image Process 28(9):4328–4338

    Article  MathSciNet  Google Scholar 

  10. Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507

    Article  MathSciNet  Google Scholar 

  11. Hinton GE, Osindero S, Teh YW (2014) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554

    Article  MathSciNet  Google Scholar 

  12. Hormozi H, Hormozi E, Nohooji HR (2012) The classification of the applicable machine learning methods in robot manipulators. Int J Mach Learn Comput 2(5):560

    Article  Google Scholar 

  13. Hu J, Lu J, Tan YP (2014) Discriminative deep metric learning for face verification in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1875–1882

  14. Huai M, Miao C, Li Y, Suo Q, Su L, Zhang A (2018) Metric learning from probabilistic labels. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pp 1541–1550

  15. Huang GB, Mattar M, Berg T, Learned-Miller E (2008) Labeled faces in the wild: a database for studying face recognition in unconstrained environments. In: Workshop on faces in ’real-life’ images: detection, alignment, and recognition, Marseille, France, October 2008. Erik Learned-Miller and Andras Ferencz and Frédéric Jurie. https://hal.inria.fr/inria-00321923

  16. Jiang L, Meng D, Yu S-I, Lan Z, Shan S, Hauptmann A (2014a) Self-paced learning with diversity. In: Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ (eds) Advances in neural information processing systems, vol 27, pp 2078–2086. Curran Associates, Inc. http://papers.nips.cc/paper/5648-self-paced-learning-with-diversity.pdf

  17. Jiang L, Meng D, Yu S-I, Lan Z, Shan S, Hauptmann A (2014b) Self-paced learning with diversity. In: Advances in neural information processing systems, pp 2078–2086

  18. Jiang L, Meng D, Zhao Q, Shan S, Hauptmann AG (2015) Self-paced curriculum learning. In: Twenty-ninth AAAI conference on artificial intelligence

  19. KalatehJari EH, Hosseini MM, Gharahbagh AA (2012) Image registration based on a novel enhanced scale invariant geometrical feature. Int J Mach Learn Comput 2(5):667

    Article  Google Scholar 

  20. Kaya M, Bilge HS (2019) Deep metric learning: a survey. Symmetry 11(9):1066

    Article  Google Scholar 

  21. Keyvanpour M, Izadpanah N, Karbasforoushan H (2012) Classification and evaluation of high-dimensional image indexing structures. Int J Mach Learn Comput 2(3):252

    Article  Google Scholar 

  22. Khan F, Mutlu B, Zhu J (2011) How do humans teach: on curriculum learning and teaching dimension. In: Advances in neural information processing systems, pp 1449–1457

  23. Kim T-K, Kittler J, Cipolla R (2007) Discriminative learning and recognition of image set classes using canonical correlations. IEEE Trans Pattern Anal Mach Intell 29(6):1005–1018

    Article  Google Scholar 

  24. Kulis B et al (2012) Metric learning: a survey. Found Trends Mach Learn 5(4):287–364

    Article  MathSciNet  Google Scholar 

  25. Kumar MP, Packer B, Koller D (2010) Self-paced learning for latent variable models. In: Advances in neural information processing systems 23: 24th annual conference on neural information processing systems, Proceedings of a meeting held 6–9 December 2010. Vancouver, British Columbia, Canada, p 2010

  26. Kwok JT, Tsang IW (2003) Learning with idealized kernels. In: Proceedings of the 20th international conference on machine learning ICML-03, pp 400–407

  27. Law MT, Thome N, Cord M (2017) Learning a distance metric from relative comparisons between quadruplets of images. Int J Comput Vis 121(1):65–94

    Article  MathSciNet  Google Scholar 

  28. Le QV, Zou WY, Yeung SY, Ng AY (2011) Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In: Computer vision & pattern recognition

  29. Lu J, Hu J, Zhou J (2017) Deep metric learning for visual understanding: an overview of recent advances. IEEE Signal Process Mag 34(6):76–84

    Article  Google Scholar 

  30. Marc, Huang FJ, Boureau Y, Lecun Y (2007) Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: IEEE conference on computer vision & pattern recognition

  31. Meng D, Xu Z, Zhang L, Zhao J (2013) A cyclic weighted median method for l1 low-rank matrix factorization with missing entries. In: Twenty-seventh AAAI conference on artificial intelligence

  32. Mignon A (2012) PCCA: a new approach for distance learning from sparse pairwise constraints. In: Computer vision & pattern recognition

  33. Méndez-Vázquez H, Martínez-Díaz Y, Chai Z (2013) Volume structured ordinal features with background similarity measure for video face recognition. In: International conference on biometrics

  34. Nguyen HV, Bai Li (2010) Cosine similarity metric learning for face verification. In: Asian conference on computer vision

  35. Nick W, Asamene K, Bullock G, Esterline A, Sundaresan M (2015) A study of machine learning techniques for detecting and classifying structural damage. Int J Mach Learn Comput 5(4):313

    Article  Google Scholar 

  36. Song HO, Xiang Y, Jegelka S, Savarese S (2016) Deep metric learning via lifted structured feature embedding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4004–4012

  37. Roth PM, Wohlhart P, Hirzer M, Kostinger M, Bischof H (2012) Large scale metric learning from equivalence constraints. In: IEEE conference on computer vision & pattern recognition

  38. Salido JAA, Ruiz C Jr (2018) Using deep learning to detect melanoma in dermoscopy images. Int J Mach Learn Comput 8(1):61–68

    Article  Google Scholar 

  39. Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 815–823

  40. Sohn Kihyuk (2016) Improved deep metric learning with multi-class n-pair loss objective. Adv Neural Inf Process Syst 29:1857–1865

    Google Scholar 

  41. Tang Y, Yang Y-B, Gao Y (2012) Self-paced dictionary learning for image classification. In: Proceedings of the 20th ACM international conference on multimedia, pp 833–836

  42. Taylor GW, Fergus R, Lecun Y, Bregler C (2010) Convolutional learning of spatio-temporal features. In: European conference on computer vision

  43. Wang R, Shan S, Chen X, Wen G (2008) Manifold-manifold distance with application to face recognition based on image set. In: IEEE computer society conference on computer vision & pattern recognition

  44. Weinshall D, Cohen G, Amir D (2018) Curriculum learning by transfer learning: theory and experiments with deep networks. arXiv preprint arXiv:1802.03796

  45. Wolf L, Hassner T, Maoz I (2011) Face recognition in unconstrained videos with matched background similarity. In: CVPR 2011. IEEE, pp 529–534

  46. Wolf L, Hassner T, Taigman Y (2009) Similarity scores based on background samples. In: Asian conference on computer vision

  47. Yeung DY, Chang H (2007) A kernel approach for semisupervised metric learning. IEEE Trans Neural Netw 18(1):141–9

    Article  Google Scholar 

  48. Yin X, Chen Q (2016) Deep metric learning autoencoder for nonlinear temporal alignment of human motion. In: 2016 IEEE international conference on robotics and automation (ICRA), pp 2160–2166

  49. Zhang D, Meng D, Han J (2016) Co-saliency detection via a self-paced multiple-instance learning framework. IEEE Trans Pattern Anal Mach Intell 39(5):865–878

    Article  Google Scholar 

  50. Zhen C, Wen L, Dong X, Shan S, Chen X (2013) Fusing robust face region descriptors via multiple metric learning for face recognition in the wild. In: Computer vision & pattern recognition

Download references

Acknowledgements

This work was supported by the National Natural Science Foundation of China under Grants 61876127 and 61732011, Natural Science Foundation of Tianjin Under Grants 17JCZDJC30800, Key Scientific and Technological Support Projects of Tianjin Key R&D Program 18YFZCGX00390 and 18YFZCGX00680.

Author information

Authors and Affiliations

  1. Intelligence and Computing School, Tianjin University, Tianjin, China

    Mohammed Al-taezi, Pengfei Zhu, Qinghua Hu & Yu Wang

  2. Computer Science Collage, Central South University, Changsha, China

    Abdulrahman Al-badwi

Authors
  1. Mohammed Al-taezi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pengfei Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qinghua Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yu Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Abdulrahman Al-badwi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohammed Al-taezi.

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

Al-taezi, M., Zhu, P., Hu, Q. et al. Self-paced hierarchical metric learning (SPHML). Int. J. Mach. Learn. & Cyber. 12, 2529–2541 (2021). https://doi.org/10.1007/s13042-021-01336-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-021-01336-2

Keywords

Search

Navigation