Learning from a single labeled face and a stream of unlabeled data

TL;DR

This paper introduces a one-class face recognition method that learns from a single labeled image and unlabeled data, achieving high accuracy with minimal false positives.

Contribution

It presents the first analysis of leveraging unlabeled data to improve single-image face recognition in a one-class setting.

Findings

Achieves 90% recognition rate with nearly zero false positives on a 43-person dataset.

Outperforms baseline methods by over 25% in recall.

Provides guidelines for parameter tuning through sensitivity analysis.

Abstract

Face recognition from a single image per person is a challenging problem because the training sample is extremely small. We consider a variation of this problem. In our problem, we recognize only one person, and there are no labeled data for any other person. This setting naturally arises in authentication on personal computers and mobile devices, and poses additional challenges because it lacks negative examples. We formalize our problem as one-class classification, and propose and analyze an algorithm that learns a non-parametric model of the face from a single labeled image and a stream of unlabeled data. In many domains, for instance when a person interacts with a computer with a camera, unlabeled data are abundant and easy to utilize. This is the first paper that investigates how these data can help in learning better models in the single-image-per-person setting. Our method is evaluated on a dataset of 43 people and we show that these people can be recognized 90% of time at nearly zero false positives. This recall is 25+% higher than the recall of our best performing baseline. Finally, we conduct a comprehensive sensitivity analysis of our algorithm and provide a guideline for setting its parameters in practice.