Advertisement

Affinity Propagation Based Closed-Form Semi-supervised Metric Learning Framework

  • Ujjal Kr DuttaEmail author
  • C. Chandra Sekhar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11139)

Abstract

Recent state-of-the-art deep metric learning approaches require large number of labeled examples for their success. They cannot directly exploit unlabeled data. When labeled data is scarce, it is very essential to be able to make use of additionally available unlabeled data to learn a distance metric in a semi-supervised manner. Despite the presence of a few traditional, non-deep semi-supervised metric learning approaches, they mostly rely on the min-max principle to encode the pairwise constraints, although there are a number of other ways as offered by traditional weakly-supervised metric learning approaches. Moreover, there is no flow of information from the available pairwise constraints to the unlabeled data, which could be beneficial. This paper proposes to learn a new metric by constraining it to be close to a prior metric while propagating the affinities among pairwise constraints to the unlabeled data via a closed-form solution. The choice of a different prior metric thus enables encoding of the pairwise constraints by following formulations other than the min-max principle.

Keywords

Mahalanobis distance Affinity propagation Metric learning Image retrieval Person re-identification Graph-based learning Semi-supervised learning Classification Fine-grained visual categorization 

References

  1. 1.
    Atzmon, Y., Shalit, U., Chechik, G.: Learning sparse metrics, one feature at a time. J. Mach. Learn. Res. (JMLR) 1, 1–48 (2015)Google Scholar
  2. 2.
    Baghshah, M.S., Shouraki, S.B.: Semi-supervised metric learning using pairwise constraints. In: Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), pp. 1217–1222 (2009)Google Scholar
  3. 3.
    Bhojanapalli, S., Boumal, N., Jain, P., Netrapalli, P.: Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form. arXiv preprint arXiv:1803.00186 (2018)
  4. 4.
    Bhojanapalli, S., Kyrillidis, A., Sanghavi, S.: Dropping convexity for faster semi-definite optimization. In: Proceedings of Conference on Learning Theory (COLT), pp. 530–582 (2016)Google Scholar
  5. 5.
    Chua, T.S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: NUS-WIDE: a real-world web image database from national university of Singapore. In: Proceedings of ACM International Conference on Image and Video Retrieval (CIVR), p. 48 (2009)Google Scholar
  6. 6.
    Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: Proceedings of International Conference on Machine Learning (ICML), pp. 209–216 (2007)Google Scholar
  7. 7.
    Dong, W., Moses, C., Li, K.: Efficient k-nearest neighbor graph construction for generic similarity measures. In: Proceedings of International Conference on World Wide Web (WWW), pp. 577–586. ACM (2011)Google Scholar
  8. 8.
    Duan, Y., Zheng, W., Lin, X., Lu, J., Zhou, J.: Deep adversarial metric learning. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2780–2789 (2018)Google Scholar
  9. 9.
    Faraki, M., Harandi, M.T., Porikli, F.: Large-scale metric learning: a voyage from shallow to deep. IEEE Trans. Neural Netw. Learn. Syst. 29(9), 4339–4346 (2018)CrossRefGoogle Scholar
  10. 10.
    Gray, D., Brennan, S., Tao, H.: Evaluating appearance models for recognition, reacquisition, and tracking. In: IEEE International Workshop on Performance Evaluation for Tracking and Surveillance (PETS), vol. 3 (2007)Google Scholar
  11. 11.
    Harandi, M., Salzmann, M., Hartley, R.: Joint dimensionality reduction and metric learning: a geometric take. In: Proceedings of International Conference on Machine Learning (ICML) (2017)Google Scholar
  12. 12.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)Google Scholar
  13. 13.
    He, X., Niyogi, P.: Locality preserving projections. In: Proceedings of Neural Information Processing Systems (NIPS), pp. 153–160 (2003)Google Scholar
  14. 14.
    Hoi, S.C., Liu, W., Chang, S.F.: Semi-supervised distance metric learning for collaborative image retrieval and clustering. ACM Trans. Multimed. Comput. Commun. Appl. 6(3), 18 (2010)CrossRefGoogle Scholar
  15. 15.
    Iscen, A., Tolias, G., Avrithis, Y., Chum, O.: Mining on manifolds: metric learning without labels. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  16. 16.
    Koestinger, M., Hirzer, M., Wohlhart, P., Roth, P.M., Bischof, H.: Large scale metric learning from equivalence constraints. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2288–2295 (2012)Google Scholar
  17. 17.
    Liu, W., Ma, S., Tao, D., Liu, J., Liu, P.: Semi-supervised sparse metric learning using alternating linearization optimization. In: Proc. of ACM International Conference on Special Interest Group on Knowledge Discovery and Data Mining (SIGKDD), pp. 1139–1148 (2010)Google Scholar
  18. 18.
    Movshovitz-Attias, Y., Toshev, A., Leung, T.K., Ioffe, S., Singh, S.: No fuss distance metric learning using proxies. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar
  19. 19.
    Niu, G., Dai, B., Yamada, M., Sugiyama, M.: Information-theoretic semi-supervised metric learning via entropy regularization. Neural Comput. 26(8), 1717–1762 (2014)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Oh Song, H., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4004–4012 (2016)Google Scholar
  21. 21.
    Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 815–823 (2015)Google Scholar
  22. 22.
    Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. In: Proceedings of Neural Information Processing Systems (NIPS), pp. 1857–1865 (2016)Google Scholar
  23. 23.
    Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015)Google Scholar
  24. 24.
    Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical report (2011)Google Scholar
  25. 25.
    Wang, J., Zhou, F., Wen, S., Liu, X., Lin, Y.: Deep metric learning with angular loss. In: Proceedings of IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar
  26. 26.
    Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. arXiv preprint arXiv:1707.00600 (2017)
  27. 27.
    Ying, S., Wen, Z., Shi, J., Peng, Y., Peng, J., Qiao, H.: Manifold preserving: an intrinsic approach for semisupervised distance metric learning. IEEE Trans. Neural Netw. Learn. Syst. (2017)Google Scholar
  28. 28.
    Zadeh, P., Hosseini, R., Sra, S.: Geometric mean metric learning. In: Proceedings of International Conference on Machine Learning (ICML), pp. 2464–2471 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringIndian Institute of Technology MadrasChennaiIndia

Personalised recommendations