Unsupervised learning of invariant feature hierarchies with applications to object recognition

Marc'Aurelio Ranzato, Fu Jie Huang, Y. Lan Boureau, Yann LeCun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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 feature-pooling layer that computes the max of each filter output within adjacent windows, and a point-wise sigmoid non-linearity. 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.

Original languageEnglish (US)
Title of host publication2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07
DOIs
StatePublished - 2007
Event2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07 - Minneapolis, MN, United States
Duration: Jun 17 2007Jun 22 2007

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Other

Other2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07
Country/TerritoryUnited States
CityMinneapolis, MN
Period6/17/076/22/07

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Unsupervised learning of invariant feature hierarchies with applications to object recognition'. Together they form a unique fingerprint.

Cite this