Dimensionality reduction by learning an invariant mapping

Raia Hadsell; Sumit Chopra; Yann LeCun

doi:10.1109/CVPR.2006.100

Dimensionality reduction by learning an invariant mapping

Raia Hadsell, Sumit Chopra, Yann LeCun

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Dimensionality reduction involves mapping a set of high dimensional input points onto a low dimensional manifold so that "similar" points in input space are mapped to nearby points on the manifold. We present a method - called Dimensionality Reduction by Learning an Invariant Mapping (DrLIM) - for learning a globally coherent nonlinear function that maps the data evenly to the output manifold. The learning relies solely on neighborhood relationships and does not require any distance measure in the input space. The method can learn mappings that are invariant to certain transformations of the inputs, as is demonstrated with a number of experiments. Comparisons are made to other techniques, in particular ILE.

Original language	English (US)
Title of host publication	Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Pages	1735-1742
Number of pages	8
DOIs	https://doi.org/10.1109/CVPR.2006.100
State	Published - 2006
Event	2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 - New York, NY, United States Duration: Jun 17 2006 → Jun 22 2006

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2
ISSN (Print)	1063-6919

Other

Other	2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Country/Territory	United States
City	New York, NY
Period	6/17/06 → 6/22/06

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2006.100

Cite this

Hadsell, R., Chopra, S., & LeCun, Y. (2006). Dimensionality reduction by learning an invariant mapping. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 (pp. 1735-1742). Article 1640964 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2). https://doi.org/10.1109/CVPR.2006.100

Dimensionality reduction by learning an invariant mapping. / Hadsell, Raia; Chopra, Sumit; LeCun, Yann.
Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. p. 1735-1742 1640964 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hadsell, R, Chopra, S & LeCun, Y 2006, Dimensionality reduction by learning an invariant mapping. in Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006., 1640964, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1735-1742, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, New York, NY, United States, 6/17/06. https://doi.org/10.1109/CVPR.2006.100

@inproceedings{c441a21f627f4b0a896fa62cb143176f,

title = "Dimensionality reduction by learning an invariant mapping",

abstract = "Dimensionality reduction involves mapping a set of high dimensional input points onto a low dimensional manifold so that {"}similar{"} points in input space are mapped to nearby points on the manifold. We present a method - called Dimensionality Reduction by Learning an Invariant Mapping (DrLIM) - for learning a globally coherent nonlinear function that maps the data evenly to the output manifold. The learning relies solely on neighborhood relationships and does not require any distance measure in the input space. The method can learn mappings that are invariant to certain transformations of the inputs, as is demonstrated with a number of experiments. Comparisons are made to other techniques, in particular ILE.",

author = "Raia Hadsell and Sumit Chopra and Yann LeCun",

year = "2006",

doi = "10.1109/CVPR.2006.100",

language = "English (US)",

isbn = "0769525970",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

pages = "1735--1742",

booktitle = "Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006",

note = "2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 ; Conference date: 17-06-2006 Through 22-06-2006",

}

TY - GEN

T1 - Dimensionality reduction by learning an invariant mapping

AU - Hadsell, Raia

AU - Chopra, Sumit

AU - LeCun, Yann

PY - 2006

Y1 - 2006

N2 - Dimensionality reduction involves mapping a set of high dimensional input points onto a low dimensional manifold so that "similar" points in input space are mapped to nearby points on the manifold. We present a method - called Dimensionality Reduction by Learning an Invariant Mapping (DrLIM) - for learning a globally coherent nonlinear function that maps the data evenly to the output manifold. The learning relies solely on neighborhood relationships and does not require any distance measure in the input space. The method can learn mappings that are invariant to certain transformations of the inputs, as is demonstrated with a number of experiments. Comparisons are made to other techniques, in particular ILE.

AB - Dimensionality reduction involves mapping a set of high dimensional input points onto a low dimensional manifold so that "similar" points in input space are mapped to nearby points on the manifold. We present a method - called Dimensionality Reduction by Learning an Invariant Mapping (DrLIM) - for learning a globally coherent nonlinear function that maps the data evenly to the output manifold. The learning relies solely on neighborhood relationships and does not require any distance measure in the input space. The method can learn mappings that are invariant to certain transformations of the inputs, as is demonstrated with a number of experiments. Comparisons are made to other techniques, in particular ILE.

UR - http://www.scopus.com/inward/record.url?scp=33845594569&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845594569&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2006.100

DO - 10.1109/CVPR.2006.100

M3 - Conference contribution

AN - SCOPUS:33845594569

SN - 0769525970

SN - 9780769525976

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1735

EP - 1742

BT - Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006

T2 - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006

Y2 - 17 June 2006 through 22 June 2006

ER -

Dimensionality reduction by learning an invariant mapping

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this