Learning invariance through imitation

Graham W. Taylor, Ian Spiro, Christoph Bregler, Rob Fergus

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

Abstract

Supervised methods for learning an embedding aim to map high-dimensional images to a space in which perceptually similar observations have high measurable similarity. Most approaches rely on binary similarity, typically defined by class membership where labels are expensive to obtain and/or difficult to define. In this paper we propose crowd-sourcing similar images by soliciting human imitations. We exploit temporal coherence in video to generate additional pairwise graded similarities between the user-contributed imitations. We introduce two methods for learning nonlinear, invariant mappings that exploit graded similarities. We learn a model that is highly effective at matching people in similar pose. It exhibits remarkable invariance to identity, clothing, background, lighting, shift and scale.

Original languageEnglish (US)
Title of host publication2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
Pages2729-2736
Number of pages8
DOIs
StatePublished - 2011
Event2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011 - Colorado Springs, CO, United States
Duration: Jun 20 2011Jun 25 2011

Other

Other2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
CountryUnited States
CityColorado Springs, CO
Period6/20/116/25/11

Fingerprint

Invariance
Labels
Lighting

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Taylor, G. W., Spiro, I., Bregler, C., & Fergus, R. (2011). Learning invariance through imitation. In 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011 (pp. 2729-2736). [5995538] https://doi.org/10.1109/CVPR.2011.5995538

Learning invariance through imitation. / Taylor, Graham W.; Spiro, Ian; Bregler, Christoph; Fergus, Rob.

2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011. 2011. p. 2729-2736 5995538.

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

Taylor, GW, Spiro, I, Bregler, C & Fergus, R 2011, Learning invariance through imitation. in 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011., 5995538, pp. 2729-2736, 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, United States, 6/20/11. https://doi.org/10.1109/CVPR.2011.5995538
Taylor GW, Spiro I, Bregler C, Fergus R. Learning invariance through imitation. In 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011. 2011. p. 2729-2736. 5995538 https://doi.org/10.1109/CVPR.2011.5995538
Taylor, Graham W. ; Spiro, Ian ; Bregler, Christoph ; Fergus, Rob. / Learning invariance through imitation. 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011. 2011. pp. 2729-2736
@inproceedings{14d1cd6c71524dc88b419f8ba7ea6a68,
title = "Learning invariance through imitation",
abstract = "Supervised methods for learning an embedding aim to map high-dimensional images to a space in which perceptually similar observations have high measurable similarity. Most approaches rely on binary similarity, typically defined by class membership where labels are expensive to obtain and/or difficult to define. In this paper we propose crowd-sourcing similar images by soliciting human imitations. We exploit temporal coherence in video to generate additional pairwise graded similarities between the user-contributed imitations. We introduce two methods for learning nonlinear, invariant mappings that exploit graded similarities. We learn a model that is highly effective at matching people in similar pose. It exhibits remarkable invariance to identity, clothing, background, lighting, shift and scale.",
author = "Taylor, {Graham W.} and Ian Spiro and Christoph Bregler and Rob Fergus",
year = "2011",
doi = "10.1109/CVPR.2011.5995538",
language = "English (US)",
isbn = "9781457703942",
pages = "2729--2736",
booktitle = "2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011",

}

TY - GEN

T1 - Learning invariance through imitation

AU - Taylor, Graham W.

AU - Spiro, Ian

AU - Bregler, Christoph

AU - Fergus, Rob

PY - 2011

Y1 - 2011

N2 - Supervised methods for learning an embedding aim to map high-dimensional images to a space in which perceptually similar observations have high measurable similarity. Most approaches rely on binary similarity, typically defined by class membership where labels are expensive to obtain and/or difficult to define. In this paper we propose crowd-sourcing similar images by soliciting human imitations. We exploit temporal coherence in video to generate additional pairwise graded similarities between the user-contributed imitations. We introduce two methods for learning nonlinear, invariant mappings that exploit graded similarities. We learn a model that is highly effective at matching people in similar pose. It exhibits remarkable invariance to identity, clothing, background, lighting, shift and scale.

AB - Supervised methods for learning an embedding aim to map high-dimensional images to a space in which perceptually similar observations have high measurable similarity. Most approaches rely on binary similarity, typically defined by class membership where labels are expensive to obtain and/or difficult to define. In this paper we propose crowd-sourcing similar images by soliciting human imitations. We exploit temporal coherence in video to generate additional pairwise graded similarities between the user-contributed imitations. We introduce two methods for learning nonlinear, invariant mappings that exploit graded similarities. We learn a model that is highly effective at matching people in similar pose. It exhibits remarkable invariance to identity, clothing, background, lighting, shift and scale.

UR - http://www.scopus.com/inward/record.url?scp=80052908982&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052908982&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2011.5995538

DO - 10.1109/CVPR.2011.5995538

M3 - Conference contribution

AN - SCOPUS:80052908982

SN - 9781457703942

SP - 2729

EP - 2736

BT - 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011

ER -