From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data

TL;DR

This paper introduces a Bayesian model that advances face recognition by enabling unsupervised identity discovery, contextual understanding, and semi-supervised learning, moving beyond traditional classification-based systems.

Contribution

It presents a novel Bayesian framework that jointly models images, identities, partial labels, and context, allowing unsupervised discovery of new identities and contextual association.

Findings

Successfully recognizes known identities with high accuracy.

Discovers new identities from unlabeled data effectively.

Handles both labeled and unlabeled faces within a unified model.

Abstract

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.