Sciweavers

CVPR
2007
IEEE

Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition

14 years 11 months ago
Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
We present an unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions. The resulting feature extractor consists of multiple convolution filters, followed by a pointwise sigmoid non-linearity, and a feature-pooling layer that computes the max of each filter output within adjacent windows. A second level of larger and more invariant features is obtained by training the same algorithm on patches of features from the first level. Training a supervised classifier on these features yields 0.64% error on MNIST, and 54% average recognition rate on Caltech 101 with 30 training samples per category. While the resulting architecture is similar to convolutional networks, the layer-wise unsupervised training procedure alleviates the over-parameterization problems that plague purely supervised learning procedures, and yields good performance with very few labeled training samples.
Marc'Aurelio Ranzato, Fu Jie Huang, Y-Lan Boureau,
Added 12 Oct 2009
Updated 12 Oct 2009
Type Conference
Year 2007
Where CVPR
Authors Marc'Aurelio Ranzato, Fu Jie Huang, Y-Lan Boureau, Yann LeCun
Comments (0)