Learning hierarchical representations for face verification with convolutional deep belief networks
Top Cited Papers
- 1 June 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2012 IEEE Conference on Computer Vision and Pattern Recognition
- p. 2518-2525
- https://doi.org/10.1109/cvpr.2012.6247968
Abstract
Most modern face recognition systems rely on a feature representation given by a hand-crafted image descriptor, such as Local Binary Patterns (LBP), and achieve improved performance by combining several such representations. In this paper, we propose deep learning as a natural source for obtaining additional, complementary representations. To learn features in high-resolution images, we make use of convolutional deep belief networks. Moreover, to take advantage of global structure in an object class, we develop local convolutional restricted Boltzmann machines, a novel convolutional learning model that exploits the global structure by not assuming stationarity of features across the image, while maintaining scalability and robustness to small misalignments. We also present a novel application of deep learning to descriptors other than pixel intensity values, such as LBP. In addition, we compare performance of networks trained using unsupervised learning against networks with random filters, and empirically show that learning weights not only is necessary for obtaining good multilayer representations, but also provides robustness to the choice of the network architecture parameters. Finally, we show that a recognition system using only representations obtained from deep learning can achieve comparable accuracy with a system using a combination of hand-crafted image descriptors. Moreover, by combining these representations, we achieve state-of-the-art results on a real-world face verification database.Keywords
This publication has 27 references indexed in Scilit:
- Unsupervised learning of hierarchical representations with convolutional deep belief networksCommunications of the ACM, 2011
- Modeling the joint density of two images under a variety of transformationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Deconvolutional networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- SENSC: a Stable and Efficient Algorithm for Nonnegative Sparse CodingActa Automatica Sinica, 2009
- What is the best multi-stage architecture for object recognition?Published by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Attribute and simile classifiers for face verificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Convolutional deep belief networks for scalable unsupervised learning of hierarchical representationsPublished by Association for Computing Machinery (ACM) ,2009
- An empirical evaluation of deep architectures on problems with many factors of variationPublished by Association for Computing Machinery (ACM) ,2007
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Text Classification from Labeled and Unlabeled Documents using EMMachine Learning, 2000