Abstract
We propose a heterogeneous multi-task learning framework on non-overlapping datasets, where each sample has only part of the labels and the size of each dataset is different. In particular, we propose two batch sampling strategies for stochastic gradient descent to learn shared CNN representation. First one sets same number of iteration on each dataset while the latter sets same batch size ratio of one task to another. We evaluate the proposed framework by learning the facial expression recognition task and facial landmark detection task. The learned network is memory efficient and able to carry out multiple tasks for one feed forward with the shared CNN. In addition, we show that the learned network achieve more robust facial landmark detection under large variation which appears in the heterogeneous dataset, though the dataset does not include landmark labels. We also investigate the effect of weights on each cost function and batch size ratio of one task to another.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sun, Y., Wang, X., Tang, X.: Deep convolutional network cascade for facial point detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3476–3483 (2013)
Zhang, Z., Luo, P., Loy, C.C., Tang, X.: Facial landmark detection by deep multi-task learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VI. LNCS, vol. 8694, pp. 94–108. Springer, Heidelberg (2014)
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1521–1528, June 2011
Cao, X., Wei, Y., Wen, F., Sun, J.: Face alignment by explicit shape regression. Int. J. Comput. Vision 107(2), 177–190 (2014)
Burgos-Artizzu, X., Perona, P., Dollár, P.: Robust face landmark estimation under occlusion. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1513–1520 (2013)
Wu, Y., Ji, Q.: Robust facial landmark detection under significant head poses and occlusion. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3658–3666 (2015)
Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. Pattern Anal. Mach. Intell. 6, 681–685 (2001)
Liu, X.: Generic face alignment using boosted appearance model. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1–8. IEEE (2007)
Asthana, A., Zafeiriou, S., Cheng, S., Pantic, M.: Robust discriminative response map fitting with constrained local models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3444–3451 (2013)
Yu, X., Huang, J., Zhang, S., Yan, W., Metaxas, D.: Pose-free facial landmark fitting via optimized part mixtures and cascaded deformable shape model. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1944–1951 (2013)
Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2879–2886. IEEE (2012)
Ekman, P., Friesen, W.V.: Manual for the Facial Action Coding System. Consulting Psychologists Press, Palo Alto (1978)
Zhao, K., Chu, W.-S., De la Torre, F., Cohn, J.F., Zhang, H.: Joint patch and multi-label learning for facial action unit detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2207–2216 (2015)
Zeng, J., Chu, W.-S., De la Torre, F., Cohn, J.F., Xiong, Z.: Confidence preserving machine for facial action unit detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3622–3630 (2015)
Rudovic, O., Pavlovic, V., Pantic, M.: Context-sensitive dynamic ordinal regression for intensity estimation of facial action units. IEEE Trans. Pattern Anal. Mach. Intell. 37(5), 944–958 (2015)
Liu, P., Han, S., Meng, Z., Tong, Y.: Facial expression recognition via a boosted deep belief network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1805–1812 (2014)
Evgeniou, T., Micchelli, C.A., Pontil, M.: Learning multiple tasks with kernel methods. J. Mach. Learn. Res. 6, 615–637 (2005)
Yu, K., Tresp, V., Schwaighofer, A.: Learning gaussian processes from multiple tasks. In: Proceedings of the 22nd International Conference on Machine Learning, ICML 2005, pp. 1012–1019. ACM, New York (2005)
Yang, X., Kim, S., Xing, E.P.: Heterogeneous multitask learning with joint sparsity constraints. In: Advances in neural information processing systems, pp. 2151–2159 (2009)
Li, S., Liu, Z.-Q., Chan, A.: Heterogeneous multi-task learning for human pose estimation with deep convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 482–489 (2014)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp. 1097–1105 (2012)
Goodfellow, I.J., et al.: Challenges in representation learning: a report on three machine learning contests. In: Lee, M., Hirose, A., Hou, Z.-G., Kil, R.M. (eds.) ICONIP 2013. LNCS, vol. 8228, pp. 117–124. Springer, Heidelberg (2013). doi:10.1007/978-3-642-42051-1_16
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Semitsu, T., Zhao, X., Matsumoto, W. (2016). Heterogeneous Multi-task Learning on Non-overlapping Datasets for Facial Landmark Detection. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds) Neural Information Processing. ICONIP 2016. Lecture Notes in Computer Science(), vol 9949. Springer, Cham. https://doi.org/10.1007/978-3-319-46675-0_68
Download citation
DOI: https://doi.org/10.1007/978-3-319-46675-0_68
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46674-3
Online ISBN: 978-3-319-46675-0
eBook Packages: Computer ScienceComputer Science (R0)