Learning localized perceptual similarity metrics for interactive categorization
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Learning localized perceptual similarity metrics for interactive categorization. / Wah, Catherine; Maji, Subhransu; Belongie, Serge.
In: Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015, 19.02.2015, p. 502-509.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Learning localized perceptual similarity metrics for interactive categorization
AU - Wah, Catherine
AU - Maji, Subhransu
AU - Belongie, Serge
N1 - Publisher Copyright: © 2015 IEEE.
PY - 2015/2/19
Y1 - 2015/2/19
N2 - Current similarity-based approaches to interactive fine grained categorization rely on learning metrics from holistic perceptual measurements of similarity between objects or images. However, making a single judgment of similarity at the object level can be a difficult or overwhelming task for the human user to perform. Secondly, a single general metric of similarity may not be able to adequately capture the minute differences that discriminate fine-grained categories. In this work, we propose a novel approach to interactive categorization that leverages multiple perceptual similarity metrics learned from localized and roughly aligned regions across images, reporting state-of-the-art results and outperforming methods that use a single nonlocalized similarity metric.
AB - Current similarity-based approaches to interactive fine grained categorization rely on learning metrics from holistic perceptual measurements of similarity between objects or images. However, making a single judgment of similarity at the object level can be a difficult or overwhelming task for the human user to perform. Secondly, a single general metric of similarity may not be able to adequately capture the minute differences that discriminate fine-grained categories. In this work, we propose a novel approach to interactive categorization that leverages multiple perceptual similarity metrics learned from localized and roughly aligned regions across images, reporting state-of-the-art results and outperforming methods that use a single nonlocalized similarity metric.
UR - http://www.scopus.com/inward/record.url?scp=84925438496&partnerID=8YFLogxK
U2 - 10.1109/WACV.2015.73
DO - 10.1109/WACV.2015.73
M3 - Conference article
AN - SCOPUS:84925438496
SP - 502
EP - 509
JO - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
JF - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
T2 - 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015
Y2 - 5 January 2015 through 9 January 2015
ER -
ID: 301829777