MULTITASK LEARNING - An Application to Incremental Face Recognition

David Masip, Àgata Lapedriza, Jordi Vitrià

Abstract

Usually face classification applications suffer from two important problems: the number of training samples from each class is reduced, and the final system usually must be extended to incorporate new people to recognize. In this paper we introduce a face recognition method that extends a previous boosting-based classifier adding new classes and avoiding the need of retraining the system each time a new person joins the system. The classifier is trained using the multitask learning principle and multiple verification tasks are trained together sharing the same feature space. The new classes are added taking advantage of the previous learned structure, being the addition of new classes not computationally demanding. Our experiments with two different data sets show that the performance does not decrease drastically even when the number of classes of the base problem is multiplied by a factor of 8.

References

  1. Baxter, J. (2000). A model of inductive bias learning. Journal of Machine Learning Research, 12:149-198.
  2. Bressan, M. and Vitria, J. (2003). Nonparametric discriminant analysis and nearest neighbor classification. Pattern Recognition Letters, 24(15):2743-2749.
  3. Caruana, R. (1997). Multitask learning. Machine Learning, 28(1):41-75.
  4. Fisher, R. (1936). The use of multiple measurements in taxonomic problems. Ann. Eugenics, 7:179-188.
  5. Freund, Y. and Schapire, R. E. (1996). Experiments with a new boosting algorithm. In International Conference on Machine Learning, pages 148-156.
  6. Friedman, J., T.Hastie, and R.Tibshirani (2000). Additive logistic regression: a statistical view of boosting. Annals of statistics, 28:337-374.
  7. Fukunaga, K. and Mantock, J. (1983). Nonparametric discriminant analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 5(6):671-678.
  8. Ji Zhu, Saharon Rosset, H. Z. and Hastie, T. (2006). Multiclass adaboost. Technical report, Standford University.
  9. Martinez, A. and Benavente, R. (1998). The AR Face database. Technical Report 24, Computer Vision Center.
  10. Masip, D., Kuncheva, L. I., and Vitria, J. (2005). An ensemble-based method for linear feature extraction for two-class problems. Pattern Analysis and Applications, 8:227-237.
  11. Phillips, P. J., Flynn, P. J., Scruggs, T., Bowyer, K. W., Chang, J., Hoffman, K., Marques, J., Min, J., and Worek, W. (2005). The 2005 IEEE workshop on face recognition grand challenge experiments. In CVPR 7805: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops, page .45, Washington, DC, USA. IEEE Computer Society.
  12. Schapire, R. E. (1997). Using output codes to boost multiclass learning problems. In Proc. 14th International Conference on Machine Learning, pages 313-321. Morgan Kaufmann.
  13. Torralba, A., Murphy, K., and Freeman, W. (2004). Sharing features: efficient boosting procedures for multiclass object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
  14. Turk, M. and Pentland, A. (1991). Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1):71-86.
  15. Yokono, J. J. and Poggio, T. (2006). A multiview face identification model with no geometric constraints. Technical report, Sony Intelligence Dynamics Laboratories.
Download


Paper Citation


in Harvard Style

Masip D., Lapedriza À. and Vitrià J. (2008). MULTITASK LEARNING - An Application to Incremental Face Recognition . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: OPRMLT, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 585-590. DOI: 10.5220/0001079205850590


in Bibtex Style

@conference{oprmlt08,
author={David Masip and Àgata Lapedriza and Jordi Vitrià},
title={MULTITASK LEARNING - An Application to Incremental Face Recognition},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: OPRMLT, (VISIGRAPP 2008)},
year={2008},
pages={585-590},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001079205850590},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: OPRMLT, (VISIGRAPP 2008)
TI - MULTITASK LEARNING - An Application to Incremental Face Recognition
SN - 978-989-8111-21-0
AU - Masip D.
AU - Lapedriza À.
AU - Vitrià J.
PY - 2008
SP - 585
EP - 590
DO - 10.5220/0001079205850590