Classification with invariant scattering representations

Joan Bruna Estrach, Stéphane Mallat

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

Abstract

A scattering transform defines a signal representation which is invariant to translations and Lipschitz continuous relatively to deformations. It is implemented with a non-linear convolution network that iterates over wavelet and modulus operators. Lipschitz continuity locally linearizes deformations. Complex classes of signals and textures can be modeled with low-dimensional affine spaces, computed with a PCA in the scattering domain. Classification is performed with a penalized model selection. State of the art results are obtained for handwritten digit recognition over small training sets, and for texture classification.

Original languageEnglish (US)
Title of host publication2011 IEEE 10th IVMSP Workshop: Perception and Visual Signal Analysis, IVMSP 2011 - Proceedings
Pages99-104
Number of pages6
DOIs
StatePublished - 2011
Event2011 IEEE 10th IVMSP Workshop: Perception and Visual Signal Analysis, IVMSP 2011 - Ithaca, NY, United States
Duration: Jun 16 2011Jun 17 2011

Other

Other2011 IEEE 10th IVMSP Workshop: Perception and Visual Signal Analysis, IVMSP 2011
CountryUnited States
CityIthaca, NY
Period6/16/116/17/11

Fingerprint

Textures
Scattering
Convolution
Mathematical operators

Keywords

  • Image classification
  • Invariant representations
  • local image descriptors
  • pattern recognition
  • texture classification

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Bruna Estrach, J., & Mallat, S. (2011). Classification with invariant scattering representations. In 2011 IEEE 10th IVMSP Workshop: Perception and Visual Signal Analysis, IVMSP 2011 - Proceedings (pp. 99-104). [5970362] https://doi.org/10.1109/IVMSPW.2011.5970362

Classification with invariant scattering representations. / Bruna Estrach, Joan; Mallat, Stéphane.

2011 IEEE 10th IVMSP Workshop: Perception and Visual Signal Analysis, IVMSP 2011 - Proceedings. 2011. p. 99-104 5970362.

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

Bruna Estrach, J & Mallat, S 2011, Classification with invariant scattering representations. in 2011 IEEE 10th IVMSP Workshop: Perception and Visual Signal Analysis, IVMSP 2011 - Proceedings., 5970362, pp. 99-104, 2011 IEEE 10th IVMSP Workshop: Perception and Visual Signal Analysis, IVMSP 2011, Ithaca, NY, United States, 6/16/11. https://doi.org/10.1109/IVMSPW.2011.5970362
Bruna Estrach J, Mallat S. Classification with invariant scattering representations. In 2011 IEEE 10th IVMSP Workshop: Perception and Visual Signal Analysis, IVMSP 2011 - Proceedings. 2011. p. 99-104. 5970362 https://doi.org/10.1109/IVMSPW.2011.5970362
Bruna Estrach, Joan ; Mallat, Stéphane. / Classification with invariant scattering representations. 2011 IEEE 10th IVMSP Workshop: Perception and Visual Signal Analysis, IVMSP 2011 - Proceedings. 2011. pp. 99-104
@inproceedings{3304a7becbfb4fc991a389896866a002,
title = "Classification with invariant scattering representations",
abstract = "A scattering transform defines a signal representation which is invariant to translations and Lipschitz continuous relatively to deformations. It is implemented with a non-linear convolution network that iterates over wavelet and modulus operators. Lipschitz continuity locally linearizes deformations. Complex classes of signals and textures can be modeled with low-dimensional affine spaces, computed with a PCA in the scattering domain. Classification is performed with a penalized model selection. State of the art results are obtained for handwritten digit recognition over small training sets, and for texture classification.",
keywords = "Image classification, Invariant representations, local image descriptors, pattern recognition, texture classification",
author = "{Bruna Estrach}, Joan and St{\'e}phane Mallat",
year = "2011",
doi = "10.1109/IVMSPW.2011.5970362",
language = "English (US)",
isbn = "9781457712869",
pages = "99--104",
booktitle = "2011 IEEE 10th IVMSP Workshop: Perception and Visual Signal Analysis, IVMSP 2011 - Proceedings",

}

TY - GEN

T1 - Classification with invariant scattering representations

AU - Bruna Estrach, Joan

AU - Mallat, Stéphane

PY - 2011

Y1 - 2011

N2 - A scattering transform defines a signal representation which is invariant to translations and Lipschitz continuous relatively to deformations. It is implemented with a non-linear convolution network that iterates over wavelet and modulus operators. Lipschitz continuity locally linearizes deformations. Complex classes of signals and textures can be modeled with low-dimensional affine spaces, computed with a PCA in the scattering domain. Classification is performed with a penalized model selection. State of the art results are obtained for handwritten digit recognition over small training sets, and for texture classification.

AB - A scattering transform defines a signal representation which is invariant to translations and Lipschitz continuous relatively to deformations. It is implemented with a non-linear convolution network that iterates over wavelet and modulus operators. Lipschitz continuity locally linearizes deformations. Complex classes of signals and textures can be modeled with low-dimensional affine spaces, computed with a PCA in the scattering domain. Classification is performed with a penalized model selection. State of the art results are obtained for handwritten digit recognition over small training sets, and for texture classification.

KW - Image classification

KW - Invariant representations

KW - local image descriptors

KW - pattern recognition

KW - texture classification

UR - http://www.scopus.com/inward/record.url?scp=80052302973&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052302973&partnerID=8YFLogxK

U2 - 10.1109/IVMSPW.2011.5970362

DO - 10.1109/IVMSPW.2011.5970362

M3 - Conference contribution

AN - SCOPUS:80052302973

SN - 9781457712869

SP - 99

EP - 104

BT - 2011 IEEE 10th IVMSP Workshop: Perception and Visual Signal Analysis, IVMSP 2011 - Proceedings

ER -