Contextual Face Recognition with a Nested-Hierarchical Nonparametric Identity Model
This addresses the limitation of current face recognition methods for applications requiring unsupervised identification, though it appears incremental as an extension of prior work.
The paper tackles the problem of face recognition systems relying on supervised classification and being unable to use unlabelled data, proposing extensions to a Bayesian model for unsupervised discovery of contexts to improve recognition.
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.