Contextual face recognition with a nested-hierarchical nonparametric identity model
File(s)
Accepted version
Author(s)
Castro, Daniel C
Nowozin, Sebastian
Type
Conference Paper
Abstract
Current face recognition systems typically operate via classification into
known identities obtained from supervised identity annotations. There are two problems with this paradigm: (1) current systems are unable to benefit from often abundant unlabelled data; and (2) they equate successful recognition with labelling a given input image. Humans, on the other hand, regularly perform identification of individuals completely unsupervised, recognising the identity of someone they have seen before even without being able to name that individual. How can we go beyond the current classification paradigm towards a more human understanding of identities? In previous work, we proposed an integrated Bayesian model that coherently reasons about the observed images, identities, partial knowledge about names, and the situational context of each observation. Here, we propose extensions of the contextual component of this model, enabling unsupervised discovery of an unbounded number of contexts for improved face recognition.
known identities obtained from supervised identity annotations. There are two problems with this paradigm: (1) current systems are unable to benefit from often abundant unlabelled data; and (2) they equate successful recognition with labelling a given input image. Humans, on the other hand, regularly perform identification of individuals completely unsupervised, recognising the identity of someone they have seen before even without being able to name that individual. How can we go beyond the current classification paradigm towards a more human understanding of identities? In previous work, we proposed an integrated Bayesian model that coherently reasons about the observed images, identities, partial knowledge about names, and the situational context of each observation. Here, we propose extensions of the contextual component of this model, enabling unsupervised discovery of an unbounded number of contexts for improved face recognition.
Date Issued
2018-12-07
Date Acceptance
2018-10-20
Citation
2018
Copyright Statement
© 2018 The Author(s)
Identifier
http://arxiv.org/abs/1811.07753v1
Source
NeurIPS 2018 Workshop on All of Bayesian Nonparametrics (BNP@NeurIPS 2018)
Subjects
cs.CV
Publication Status
Published online
Start Date
2018-12-07
Coverage Spatial
Montréal, Canada