Convolutional neural networks applied to house numbers digit classification

Pierre Sermanet, Soumith Chintala, Yann LeCun

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

Abstract

We classify digits of real-world house numbers using convolutional neural networks (ConvNets). Con-vNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 95.10% accuracy on the SVHN dataset (48% error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net.

Original languageEnglish (US)
Title of host publicationICPR 2012 - 21st International Conference on Pattern Recognition
Pages3288-3291
Number of pages4
StatePublished - 2012
Event21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan
Duration: Nov 11 2012Nov 15 2012

Other

Other21st International Conference on Pattern Recognition, ICPR 2012
CountryJapan
CityTsukuba
Period11/11/1211/15/12

Fingerprint

Neural networks

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Sermanet, P., Chintala, S., & LeCun, Y. (2012). Convolutional neural networks applied to house numbers digit classification. In ICPR 2012 - 21st International Conference on Pattern Recognition (pp. 3288-3291). [6460867]

Convolutional neural networks applied to house numbers digit classification. / Sermanet, Pierre; Chintala, Soumith; LeCun, Yann.

ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. p. 3288-3291 6460867.

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

Sermanet, P, Chintala, S & LeCun, Y 2012, Convolutional neural networks applied to house numbers digit classification. in ICPR 2012 - 21st International Conference on Pattern Recognition., 6460867, pp. 3288-3291, 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, 11/11/12.
Sermanet P, Chintala S, LeCun Y. Convolutional neural networks applied to house numbers digit classification. In ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. p. 3288-3291. 6460867
Sermanet, Pierre ; Chintala, Soumith ; LeCun, Yann. / Convolutional neural networks applied to house numbers digit classification. ICPR 2012 - 21st International Conference on Pattern Recognition. 2012. pp. 3288-3291
@inproceedings{b3a0b21622df4988b2d904126f2c92e2,
title = "Convolutional neural networks applied to house numbers digit classification",
abstract = "We classify digits of real-world house numbers using convolutional neural networks (ConvNets). Con-vNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 95.10{\%} accuracy on the SVHN dataset (48{\%} error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net.",
author = "Pierre Sermanet and Soumith Chintala and Yann LeCun",
year = "2012",
language = "English (US)",
isbn = "9784990644109",
pages = "3288--3291",
booktitle = "ICPR 2012 - 21st International Conference on Pattern Recognition",

}

TY - GEN

T1 - Convolutional neural networks applied to house numbers digit classification

AU - Sermanet, Pierre

AU - Chintala, Soumith

AU - LeCun, Yann

PY - 2012

Y1 - 2012

N2 - We classify digits of real-world house numbers using convolutional neural networks (ConvNets). Con-vNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 95.10% accuracy on the SVHN dataset (48% error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net.

AB - We classify digits of real-world house numbers using convolutional neural networks (ConvNets). Con-vNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 95.10% accuracy on the SVHN dataset (48% error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net.

UR - http://www.scopus.com/inward/record.url?scp=84874575248&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874575248&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9784990644109

SP - 3288

EP - 3291

BT - ICPR 2012 - 21st International Conference on Pattern Recognition

ER -