Abstract
Prior work has reported the benefit of transfer learning on domains of single output tasks for classification or prediction of a scalar. We investigate the use of transfer learning on a domain of tasks where each task has multiple outputs (ie. output is a vector). Multiple Task Learning (MTL) and Context-sensitive Multiple Task Learning (csMTL) neural networks are considered for a domain of image transformation tasks. Models are developed to transform images of neutral human faces to that of corresponding images of angry, happy and sad faces. The MTL approach proves problematic because the size of the network grows as a multiplicative function of the number of outputs and number of tasks. Empirical results show that csMTL neural networks are capable of developing superior models to single task learning models when beneficial transfer occurs from one or more secondary tasks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Baxter, J.: Learning model bias. In: Touretzky, D.S., Pmozer, M.C., Hasselmo, M.E. (eds.) Advances in Neural Information Processing Systems, vol. 8, pp. 169–175. MIT Press (1996)
Bengio, Y., Delalleau, O.: On the Expressive Power of Deep Architectures. In: Kivinen, J., Szepesvári, C., Ukkonen, E., Zeugmann, T. (eds.) ALT 2011. LNCS, vol. 6925, pp. 18–36. Springer, Heidelberg (2011)
Bichsel, M.: Automatic interpolation and recognition of face images by morphing. In: Proc. of the 2nd Int. Conf. on Automatic Face and Gesture Recognition (FG 1996), pp. 128–136. IEEE Computer Society, Washington, DC (1996)
Caruana, R.A.: Multitask learning. Machine Learning 28, 41–75 (1997)
Kanade, T., Cohn, J.F., Tian, Y.: Comprehensive database for facial expression analysis. In: Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition (FG 2000), Grenoble, France, pp. 46–53 (1988)
Kharat, G.U., Dudul, S.V.: Neural network classifier for human emotion recognition from facial expressions using discrete cosine transform. In: Proc. of the 2008 First Int. Conf. on Emerging Trends in Engineering and Technology, pp. 653–658. IEEE Computer Society, Washington, DC (2008)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Silver, D.L., Bennett, K.P.: Special issue on inductive transfer. Machine Learning 73 (2008)
Silver, D.L., Mercer, R.E.: The parallel transfer of task knowledge using dynamic learning rates based on a measure of relatedness. In: Thrun, S., Pratt, L.Y. (eds.) Learning to Learn, pp. 213–233. Kluwer Academic Publisher, Boston (1997)
Silver, D.L., Poirier, R., Currie, D.: Inductive transfer with context-sensitive neural networks. Machine Learning 73, 323–336 (2008)
Silver, D.L., Tu, L.: Image Transformation: Inductive Transfer between Multiple Tasks Having Multiple Outputs. In: Bergler, S. (ed.) Canadian AI 2008. LNCS (LNAI), vol. 5032, pp. 296–307. Springer, Heidelberg (2008)
Tu, L.: Image Morphing: Inductive Transfer between Tasks that have Multiple Outputs. MSc Thesis, School of Computer Science, Acadia University, Wolfville, NS (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Silver, D.L., Tu, L. (2012). Image Morphing: Transfer Learning between Tasks That Have Multiple Outputs. In: Kosseim, L., Inkpen, D. (eds) Advances in Artificial Intelligence. Canadian AI 2012. Lecture Notes in Computer Science(), vol 7310. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-30353-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-30353-1_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-30352-4
Online ISBN: 978-3-642-30353-1
eBook Packages: Computer ScienceComputer Science (R0)