This is a series of projects whose goal is to produce
category-level object recognition systems with state of the art
performance that can run in real time. The systems are hierarchical
(multi-stage) and use "deep learning" methods (unsupervised and
supervised) to train the features at all levels. A convolutional
network pre-trained with sparse coding methods and refined with
supervised gradient descent achieves over 70% correct recognition rate
on the Caltech-101 dataset. Another system based on SIFT for low-level
features and high-dimensional sparse coding for mid-level features
achieved over 75% on Caltech-101.
Latest Video
Watch the real-time demo of our object recognition being trained on the fly.
Publications
147.
Y-Lan Boureau, Jean Ponce and Yann LeCun: A theoretical analysis of feature pooling in vision algorithms, Proc. International Conference on Machine learning (ICML'10), 2010, \cite{boureau-icml-10}.
Y-Lan Boureau, Francis Bach, Yann LeCun and Jean Ponce: Learning Mid-Level Features for Recognition, Proc. International Conference on Computer Vision and Pattern Recognition (CVPR'10), IEEE, 2010, \cite{boureau-cvpr-10}.
Kevin Jarrett, Koray Kavukcuoglu, Marc'Aurelio Ranzato and Yann LeCun: What is the Best Multi-Stage Architecture for Object Recognition?, Proc. International Conference on Computer Vision (ICCV'09), IEEE, 2009, \cite{jarrett-iccv-09}.
Koray Kavukcuoglu, Marc'Aurelio Ranzato, Rob Fergus and Yann LeCun: Learning Invariant Features through Topographic Filter Maps, Proc. International Conference on Computer Vision and Pattern Recognition (CVPR'09), IEEE, 2009, \cite{koray-cvpr-09}.
Marc'Aurelio Ranzato, Y-Lan Boureau and Yann LeCun: Sparse feature learning for deep belief networks, Advances in Neural Information Processing Systems (NIPS 2007), 2007, \cite{ranzato-nips-07}.
Marc'Aurelio Ranzato and Yann LeCun: A Sparse and Locally Shift Invariant Feature Extractor Applied to Document Images, Proc. International Conference on Document Analysis and Recognition (ICDAR), 2007, \cite{ranzato-icdar-07}.
Marc'Aurelio Ranzato, Y-Lan Boureau, Sumit Chopra and Yann LeCun: A Unified Energy-Based Framework for Unsupervised Learning, Proc. Conference on AI and Statistics (AI-Stats), 2007, \cite{ranzato-unsup-07}.
Marc'Aurelio Ranzato, Christopher Poultney, Sumit Chopra and Yann LeCun: Efficient Learning of Sparse Representations with an Energy-Based Model, in J. Platt et al. (Eds), Advances in Neural Information Processing Systems (NIPS 2006), MIT Press, 2006, \cite{ranzato-06}.
