Abstract
The artificial neural networks that are used to recognize shapes typically use one or more layers of learned feature detectors that produce scalar outputs. By contrast, the computer vision community uses complicated, hand-engineered features, like SIFT [6], that produce a whole vector of outputs including an explicit representation of the pose of the feature. We show how neural networks can be used to learn features that output a whole vector of instantiation parameters and we argue that this is a much more promising way of dealing with variations in position, orientation, scale and lighting than the methods currently employed in the neural networks community. It is also more promising than the hand-engineered features currently used in computer vision because it provides an efficient way of adapting the features to the domain.
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.
References
Berkes, P., Turner, R.E., Sahani, M.: A structured model of video reproduces primary visual cortical organisation. PLoS Computational Biology 5(9), 1–16 (2009)
Freeman, W., Adelson, E.: The design and use of steerable filters. IEEE Transactions on Pattern Analysis and Machine Intelligence 13(9), 891–906 (1991)
Hinton, G.E.: Shape representation in parallel systems. In: Proc. 7th International Joint Conference on Artificial Intelligence, vol. 2, pp. 1088–1096 (1981)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11), 2278–2324 (1998)
Lee, H., Grosse, R., Ranganath, R., Ng, A.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In: Proc. 26th International Conference on Machine Learning (2009)
Lowe, D.G.: Object recognition from local scale-invariant features. In: Proc. International Conference on Computer Vision (1999)
Memisevic, R., Hinton, G.: Learning to represent spatial transformations with factored higher-order boltzmann machines. Neural Comp. 22, 1473–1492 (2010)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proc. 27th International Conference on Machine Learning (2010)
Pelli, D.G., Tillman, K.A.: The uncrowded window of object recognition. Nature Neuroscience 11, 1129–1135 (2008)
Ranzato, M., Huang, F., Boureau, Y., LeCun, Y.: Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: Proc. Computer Vision and Pattern Recognition Conference (CVPR 2007). IEEE Press, Los Alamitos (2007)
Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nature Neuroscience 2, 1019–1025 (1999)
Zemel, R.S., Mozer, M.C., Hinton, G.E.: Traffic: Recognizing objects using hier-archical reference frame transformations. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, pp. 266–273. Morgan Kauffman, San Mateo (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hinton, G.E., Krizhevsky, A., Wang, S.D. (2011). Transforming Auto-Encoders. In: Honkela, T., Duch, W., Girolami, M., Kaski, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2011. ICANN 2011. Lecture Notes in Computer Science, vol 6791. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21735-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-21735-7_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21734-0
Online ISBN: 978-3-642-21735-7
eBook Packages: Computer ScienceComputer Science (R0)