From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data
This work addresses the problem of enabling face recognition systems to handle unlabeled data and discover unknown identities, which is incremental as it builds on existing paradigms with a novel integrated approach.
The paper tackles the limitation of current face recognition systems that rely on supervised classification and cannot utilize unlabeled data, proposing a Bayesian model that achieves good recognition performance on known identities while discovering new identities from unsupervised data and learning context associations.
Current face recognition systems robustly recognize identities across a wide variety of imaging conditions. In these systems recognition is performed via classification into known identities obtained from supervised identity annotations. There are two problems with this current paradigm: (1) current systems are unable to benefit from unlabelled data which may be available in large quantities; and (2) current systems 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? We propose an integrated Bayesian model that coherently reasons about the observed images, identities, partial knowledge about names, and the situational context of each observation. While our model achieves good recognition performance against known identities, it can also discover new identities from unsupervised data and learns to associate identities with different contexts depending on which identities tend to be observed together. In addition, the proposed semi-supervised component is able to handle not only acquaintances, whose names are known, but also unlabelled familiar faces and complete strangers in a unified framework.