TY - GEN
T1 - Learning a similarity metric discriminatively, with application to face verification
AU - Chopra, Sumit
AU - Hadsell, Raia
AU - LeCun, Yann
PY - 2005
Y1 - 2005
N2 - We present a method for training a similarity metric from data. The method can be used for recognition or verification applications where the number of categories is very large and not known during training, and where the number of training samples for a single category is very small. The idea is to learn a function that maps input patterns into a target space such that the L 1 norm in the target space approximates the "semantic" distance in the input space. The method is applied to a face verification task. The learning process minimizes a discriminative loss function that drives the similarity metric to be small for pairs of faces from the same person, and large for pairs from different persons. The mapping from raw to the target space is a convolutional network whose architecture is designed for robustness to geometric distortions. The system is tested on the Purdue/AR face database which has a very high degree of variability in the pose, lighting, expression, position, and artificial occlusions such as dark glasses and obscuring scarves.
AB - We present a method for training a similarity metric from data. The method can be used for recognition or verification applications where the number of categories is very large and not known during training, and where the number of training samples for a single category is very small. The idea is to learn a function that maps input patterns into a target space such that the L 1 norm in the target space approximates the "semantic" distance in the input space. The method is applied to a face verification task. The learning process minimizes a discriminative loss function that drives the similarity metric to be small for pairs of faces from the same person, and large for pairs from different persons. The mapping from raw to the target space is a convolutional network whose architecture is designed for robustness to geometric distortions. The system is tested on the Purdue/AR face database which has a very high degree of variability in the pose, lighting, expression, position, and artificial occlusions such as dark glasses and obscuring scarves.
UR - http://www.scopus.com/inward/record.url?scp=24644436425&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=24644436425&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2005.202
DO - 10.1109/CVPR.2005.202
M3 - Conference contribution
AN - SCOPUS:24644436425
SN - 0769523722
SN - 9780769523729
T3 - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
SP - 539
EP - 546
BT - Proceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
PB - IEEE Computer Society
T2 - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
Y2 - 20 June 2005 through 25 June 2005
ER -