Abstract
Decision forests are an increasingly popular tool in computer vision problems. Their advantages include high computational efficiency, state-of-the-art accuracy and multi-class support. In this paper, we present a novel method for transfer learning which uses decision forests, and we apply it to recognize gestures and characters. We introduce two mechanisms into the decision forest framework in order to transfer knowledge from the source tasks to a given target task. The first one is mixed information gain, which is a data-based regularizer. The second one is label propagation, which infers the manifold structure of the feature space. We show that both of them are important to achieve higher accuracy. Our experiments demonstrate improvements over traditional decision forests in the ChaLearn Gesture Challenge and MNIST data set. They also compare favorably against other state-of-the-art classifiers.
Editors: Isabelle Guyon, Vassilis Athitsos, and Sergio Escalera
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
M.A.R. Ahad, J.K. Tan, H. Kim, S. Ishikawa, Motion history image: its variants and applications. Mach. Vis. Appl. 23(2), 255–281 (2012)
Y. Aytar, A. Zisserman, Tabula rasa: model transfer for object category detection, in Proceedings of the IEEE Computer Vision and Pattern Recognition, 2011
E. Bart, S. Ullman, Cross-generalization: learning novel classes from a single example by feature replacement, in Proceedings of the IEEE Computer Vision and Pattern Recognition, 2005
A. Bergamo, L. Torresani, Exploiting weakly-labeled web images to improve object classification: a domain adaptation approach, in Proceedings of the Advances in Neural Information Processing Systems, 2010, pp. 181–189
A. Bobick, J. Davis, An appearance-based representation of action, in Proceedings of the International Conference on Pattern Recognition, 1996, pp. 307–312
A. Bobick, J. Davis. The recognition of human movement using temporal templates. IEEE Trans. Pattern Anal. Mach., 2001
R. Bowden, D. Windridge, T. Kadir, A. Zisserman, J. M. Brady. A linguistic feature vector for the visual interpretation of sign language, in Proceedings of the European Conference on Computer Vision, 2004
L. Breiman, Random forests. Mach. Learn. 45(1), 5–32 (2001)
T.M. Cover, J.A. Thomas, Elements of Information Theory (Wiley, Hoboken, 2006)
A. Criminisi, J. Shotton, E. Konukoglu, Decision forests: a unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Found. Trends Comput. Graph. Vis. 7(2–3), 81–227 (2012)
W. Dai, Q. Yang, G.R. Xue, Y. Yu, Boosting for transfer learning, in Proceedings of the International Conference on Machine Learning, New York, NY, USA, 2007, p. 193–200
J.B. Faddoul, B. Chidlovskii, R. Gilleron, F. Torre, Learning multiple tasks with boosted decision trees, in Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, 2012
A. Farhadi, D. Forsyth, R. White, Transfer learning in sign language, in Proceedings of the IEEE Computer Vision and Pattern Recognition, 2007, pp. 1–8
L. Fei-Fei, R. Fergus, P. Perona, One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. 28(4), 594–611 (2006)
Pedro F. Felzenszwalb, Ross B. Girshick, David A. McAllester, Deva Ramanan, Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. 32(9), 1627–1645 (2010)
Y. Freund, R.E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997)
R. Gopalan, R. Li, R. Chellappa, Domain adaptation for object recognition: an unsupervised approach, in Proceedings of the IEEE International Conference on Computer Vision, 2011, pp. 999–1006
E. Grosicki, H.E. Abed, ICDAR 2011 - French handwriting recognition competition, in Proceedings of the International Conference on Document Analysis and Recognition, 2011, pp. 1459–1463
I. Guyon, V. Athitsos, P. Jangyodsuk, B. Hamner, H.J. Escalante, ChaLearn gesture challenge: design and first results, in Workshop on Gesture Recognition and Kinect Demonstration Competition, 2012
I. Guyon, V. Athitsos, P. Jangyodsuk, H.J. Escalante, B. Hamner, Results and analysis of the ChaLearn gesture challenge 2012, in Advances in Depth Image Analysis and Applications, vol. 7854 of Lecture Notes in Computer Science (Springer, New York, 2013), pp. 186–204
T. Hastie, R. Tibshirani, J.H. Friedman, The Elements of Statistical Learning. (Springer, New York, 2003)
A. Kurakin, Z. Zhang, Z. Liu, A real-time system for dynamic hand gesture recognition with a depth sensor, in Proceedings of the European Signal Processing Conference, 2012, pp. 1980–1984
Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, in Proceedings of the IEEE, 1998, pp. 2278–2324
C. Leistner, A. Saffari, J. Santner, H. Bischof, Semi-supervised random forests, in Proceedings of the IEEE International Conference on Computer Vision, 2009, pp. 506–513
K. Levi, M. Fink, Y. Weiss. Learning from a small number of training examples by exploiting object categories, in Proceedings of the IEEE Computer Vision and Pattern Recognition Workshop, 2004, pp. 96–102
W. Li, Z. Zhang, Z. Liu, Graphical modeling and decoding of human actions, in Proceedings of the IEEE International Workshop on Multimedia Signal Processing, 2008, pp. 175–180
J.J. Lim, R. Salakhutdinov, A. Torralba, Transfer learning by borrowing examples for multiclass object detection, in Proceedings of the Advances in Neural Information Processing Systems, 2011
J. Liu, K. Yu, Y. Zhang, Y. Huang, Training conditional random fields using transfer learning for gesture recognition, in Proceedings of the IEEE International Conference on Data Mining, 2010, pp. 314–323
Y.M. Lui, Human gesture recognition on product manifolds. J. Mach. Learn. Res. 13, 3297–3321 (2012)
M.R. Malgireddy, I. Nwogu, V. Govindaraju, Language-motivated approaches to action recognition. J. Mach. Learn. Res. 14, 2189–2212 (2013)
S.J. Pan, Q. Yang, A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359, October 2010. ISSN 1041-4347
Y. Pei, T.-K. Kim, H. Zha, Unsupervised random forest manifold alignment for lipreading, in Proceedings of the IEEE International Conference on Computer Vision, 2013
N. Quadrianto, A.J Smola, T. Caetano, S.V.N. Vishwanathanand, J. Petterson, Multitask learning without label correspondences, in Proceedings of the Advances in Neural Information Processing Systems, 2010
A. Quattoni, M. Collins, T. Darrell, Transfer learning for image classification with sparse prototype representations, in Proceedings of the IEEE Computer Vision and Pattern Recognition, 2008, pp. 1–8
J.R. Quinlan, Induction of decision trees. Mach. Learn. 1(1), 81–106 (1986)
K. Saenko, B. Kulis, M. Fritz, T. Darrell. Adapting visual category models to new domains, in Proceedings of the European Conference on Computer Vision, 2010, pp. 213–226
H.J. Seo, P. Milanfar, Action recognition from one example. IEEE Trans. Pattern Anal. Mach. 33(5), 867–882 (2011)
T. Sharp, Implementing decision trees and forests on a GPU, in Proceedings of the European Conference on Computer Vision, 2008, pp. 595–608
E.B. Sudderth, A. Torralba, W.T. Freeman, A.S. Willsky, Learning hierarchical models of scenes, objects, and parts, in Proceedings of the IEEE International Conference on Computer Vision, 2005, pp. 1331–1338
T. Tommasi, F. Orabona, B. Caputo, Learning categories from few examples with multi model knowledge transfer. IEEE Trans. Pattern Anal. Mach. 36(5), 928–941 (2014)
A. Torralba, K.P. Murphy, W.T. Freeman, Sharing visual features for multiclass and multiview object detection. IEEE Trans. Pattern Anal. Mach. 29(5), 854–869 (2007)
P.A. Viola, M.J. Jones, Robust real-time face detection. Int. J. Comput. Vis. 57(2), 137–154 (2004)
J. Wan, Q. Ruan, W. Li, S. Deng, One-shot learning gesture recognition from RGB-D data using bag of features. J. Mach. Learn. Res. 14, 2549–2582 (2013)
Q. Wang, L. Zhang, M. Chi, J. Guo, MTForest: ensemble decision trees based on multi-task learning, in Proceedings of the European Conference on Artificial Intelligence, 2008, pp. 122–126
J. won Lee, C. Giraud-Carrier, Transfer learning in decision trees, in Proceedings of the International Joint Conference on Neural Networks, 2007
Y. Yao, G. Doretto, Boosting for transfer learning with multiple sources, in Proceedings of the IEEE Computer Vision and Pattern Recognition, 2010, pp. 1855–1862
Acknowledgements
We would like to thank Zicheng Liu and Julio Jacobo-Berlles for their feedback and assistance.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix A
Appendix A
We prove Theorem 1. First, we prove \({\mathbb {E}}(\mathcal{H}(S_K)) + \sum _{\mathbf {y}\in \mathcal{Y}} p_{\mathbf {y}} \log \left( 1 + \frac{1 - p_{\mathbf {y}}}{K p_{\mathbf {y}}} \right) \le \mathcal{H}({P}) \)
By definition of the empirical entropy and linearity of the expectation, we have:
Using the definitions of the empirical histogram \(\hat{p}_{S_K}(\mathbf {y})\) and the expectation:
Assuming that the samples are iid, then:
Note that, in this equation, \(p_{\mathbf {y}}\) is the true probability of distribution \({P}\). After some algebraic manipulations, we obtain the following:
Applying Jensen’s inequality for the convex function \(-\log (x)\), we obtain:
Now we prove \(\mathcal{H}({P}) \le {\mathbb {E}}(\mathcal{H}(S_K))\).
By definition of the empirical entropy and linearity of the expectation, we have:
Applying Jensen’s inequality for the convex function \( x \log x\), we obtain the following:
Since \({\mathbb {E}}\left[ \hat{p}_{S_K}(\mathbf {y}) \right] = p_{\mathbf {y}}\), we have:
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Goussies, N.A., Ubalde, S., Mejail, M. (2017). Transfer Learning Decision Forests for Gesture Recognition. In: Escalera, S., Guyon, I., Athitsos, V. (eds) Gesture Recognition. The Springer Series on Challenges in Machine Learning. Springer, Cham. https://doi.org/10.1007/978-3-319-57021-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-57021-1_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-57020-4
Online ISBN: 978-3-319-57021-1
eBook Packages: Computer ScienceComputer Science (R0)