Learning from a Single Labeled Face and a Stream of Unlabeled Data - Archive ouverte HAL Access content directly
Conference Papers Year :

Learning from a Single Labeled Face and a Stream of Unlabeled Data

(1) , (2)
Michal Valko


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.
Fichier principal
Vignette du fichier
kveton2013learning.pdf (1.21 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00749197 , version 1 (17-01-2013)
hal-00749197 , version 2 (18-01-2013)


  • HAL Id : hal-00749197 , version 2


Branislav Kveton, Michal Valko. Learning from a Single Labeled Face and a Stream of Unlabeled Data. 10th IEEE International Conference on Automatic Face and Gesture Recognition, Apr 2013, Shanghai, China. ⟨hal-00749197v2⟩
236 View
159 Download


Gmail Facebook Twitter LinkedIn More