From region similarity to category discovery

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Standard

From region similarity to category discovery. / Galleguillos, Carolina; Mcfee, Brian; Belongie, Serge; Lanckriet, Gert.

I: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011, s. 2665-2672.

Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt

Harvard

Galleguillos, C, Mcfee, B, Belongie, S & Lanckriet, G 2011, 'From region similarity to category discovery', Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, s. 2665-2672. https://doi.org/10.1109/CVPR.2011.5995527

APA

Galleguillos, C., Mcfee, B., Belongie, S., & Lanckriet, G. (2011). From region similarity to category discovery. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2665-2672. https://doi.org/10.1109/CVPR.2011.5995527

Vancouver

Galleguillos C, Mcfee B, Belongie S, Lanckriet G. From region similarity to category discovery. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2011;2665-2672. https://doi.org/10.1109/CVPR.2011.5995527

Author

Galleguillos, Carolina ; Mcfee, Brian ; Belongie, Serge ; Lanckriet, Gert. / From region similarity to category discovery. I: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2011 ; s. 2665-2672.

Bibtex

@inproceedings{70e451795ad14ea4a4ad8e2e9aba2eda,
title = "From region similarity to category discovery",
abstract = "The goal of object category discovery is to automatically identify groups of image regions which belong to some new, previously unseen category. This task is typically performed in a purely unsupervised setting, and as a result, performance depends critically upon accurate assessments of similarity between unlabeled image regions. To improve the accuracy of category discovery, we develop a novel multiple kernel learning algorithm based on structural SVM, which optimizes a similarity space for nearest-neighbor prediction. The optimized space is then used to cluster unlabeled data and identify new categories. Experimental results on the MSRC and PASCAL VOC2007 data sets indicate that using an optimized similarity metric can improve clustering for category discovery. Furthermore, we demonstrate that including both labeled and unlabeled training data when optimizing the similarity metric can improve the overall quality of the system.",
author = "Carolina Galleguillos and Brian Mcfee and Serge Belongie and Gert Lanckriet",
year = "2011",
doi = "10.1109/CVPR.2011.5995527",
language = "English",
pages = "2665--2672",
journal = "I E E E Conference on Computer Vision and Pattern Recognition. Proceedings",
issn = "1063-6919",
publisher = "Institute of Electrical and Electronics Engineers",

}

RIS

TY - GEN

T1 - From region similarity to category discovery

AU - Galleguillos, Carolina

AU - Mcfee, Brian

AU - Belongie, Serge

AU - Lanckriet, Gert

PY - 2011

Y1 - 2011

N2 - The goal of object category discovery is to automatically identify groups of image regions which belong to some new, previously unseen category. This task is typically performed in a purely unsupervised setting, and as a result, performance depends critically upon accurate assessments of similarity between unlabeled image regions. To improve the accuracy of category discovery, we develop a novel multiple kernel learning algorithm based on structural SVM, which optimizes a similarity space for nearest-neighbor prediction. The optimized space is then used to cluster unlabeled data and identify new categories. Experimental results on the MSRC and PASCAL VOC2007 data sets indicate that using an optimized similarity metric can improve clustering for category discovery. Furthermore, we demonstrate that including both labeled and unlabeled training data when optimizing the similarity metric can improve the overall quality of the system.

AB - The goal of object category discovery is to automatically identify groups of image regions which belong to some new, previously unseen category. This task is typically performed in a purely unsupervised setting, and as a result, performance depends critically upon accurate assessments of similarity between unlabeled image regions. To improve the accuracy of category discovery, we develop a novel multiple kernel learning algorithm based on structural SVM, which optimizes a similarity space for nearest-neighbor prediction. The optimized space is then used to cluster unlabeled data and identify new categories. Experimental results on the MSRC and PASCAL VOC2007 data sets indicate that using an optimized similarity metric can improve clustering for category discovery. Furthermore, we demonstrate that including both labeled and unlabeled training data when optimizing the similarity metric can improve the overall quality of the system.

UR - http://www.scopus.com/inward/record.url?scp=80052882493&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2011.5995527

DO - 10.1109/CVPR.2011.5995527

M3 - Conference article

AN - SCOPUS:80052882493

SP - 2665

EP - 2672

JO - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings

JF - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings

SN - 1063-6919

ER -

ID: 301831198