TY - GEN

T1 - Attribute-based detection of unfamiliar classes with humans in the loop

AU - Wah, Catherine

AU - Belongie, Serge

PY - 2013

Y1 - 2013

N2 - Recent work in computer vision has addressed zero-shot learning or unseen class detection, which involves categorizing objects without observing any training examples. However, these problems assume that attributes or defining characteristics of these unobserved classes are known, leveraging this information at test time to detect an unseen class. We address the more realistic problem of detecting categories that do not appear in the dataset in any form. We denote such a category as an unfamiliar class, it is neither observed at train time, nor do we possess any knowledge regarding its relationships to attributes. This problem is one that has received limited attention within the computer vision community. In this work, we propose a novel approach to the unfamiliar class detection task that builds on attribute-based classification methods, and we empirically demonstrate how classification accuracy is impacted by attribute noise and dataset 'difficulty,' as quantified by the separation of classes in the attribute space. We also present a method for incorporating human users to overcome deficiencies in attribute detection. We demonstrate results superior to existing methods on the challenging CUB-200-2011 dataset.

AB - Recent work in computer vision has addressed zero-shot learning or unseen class detection, which involves categorizing objects without observing any training examples. However, these problems assume that attributes or defining characteristics of these unobserved classes are known, leveraging this information at test time to detect an unseen class. We address the more realistic problem of detecting categories that do not appear in the dataset in any form. We denote such a category as an unfamiliar class, it is neither observed at train time, nor do we possess any knowledge regarding its relationships to attributes. This problem is one that has received limited attention within the computer vision community. In this work, we propose a novel approach to the unfamiliar class detection task that builds on attribute-based classification methods, and we empirically demonstrate how classification accuracy is impacted by attribute noise and dataset 'difficulty,' as quantified by the separation of classes in the attribute space. We also present a method for incorporating human users to overcome deficiencies in attribute detection. We demonstrate results superior to existing methods on the challenging CUB-200-2011 dataset.

KW - attribute-based classification

KW - fine-grained visual categories

KW - human in the loop

KW - unfamiliar class detection

KW - visual recognition

UR - http://www.scopus.com/inward/record.url?scp=84887334314&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2013.106

DO - 10.1109/CVPR.2013.106

M3 - Conference article

AN - SCOPUS:84887334314

SP - 779

EP - 786

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

M1 - 6618950

T2 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013

Y2 - 23 June 2013 through 28 June 2013

ER -