From region similarity to category discovery
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
From region similarity to category discovery. / Galleguillos, Carolina; Mcfee, Brian; Belongie, Serge; Lanckriet, Gert.
In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011, p. 2665-2672.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
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