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/sub 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.
Learning a similarity metric discriminatively, with application to face verification
2005-01-01
600976 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Set2Model networks: Learning discriminatively to learn generative models
British Library Online Contents | 2018
|Discriminatively Learned Hierarchical Rank Pooling Networks
British Library Online Contents | 2017
|Vehicle Detection Using Discriminatively Trained Part Templates with Variable Size
British Library Conference Proceedings | 2012
|