Multiple one-shots for utilizing class label information

Yaniv Taigman, Lior Wolf, Tal Hassner

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

153 Scopus citations

Abstract

The One-Shot Similarity measure has recently been introduced as a means of boosting the performance of face recognition systems. Given two vectors, their One-Shot Similarity score reflects the likelihood of each vector belonging to the same class as the other vector and not in a class defined by a fixed set of "negative™ examples. An appealing aspect of this approach is that it does not require class labeled training data. In this paper we explore how the One-Shot Similarity may nevertheless benefit from the availability of such labels. We make the following contributions: (a) we present a system utilizing subject and pose information to improve facial image pair-matching performance using multiple One-Shot scores; (b) we show how separating pose and identity may lead to better face recognition rates in unconstrained, "wild™ facial images; (c) we explore how far we can get using a single descriptor with different similarity tests as opposed to the popular multiple descriptor approaches; and (d) we demonstrate the benefit of learned metrics for improved One-Shot performance. We test the performance of our system on the challenging Labeled Faces in the Wild unrestricted benchmark and present results that exceed by a large margin results reported on the restricted benchmark.

Original languageEnglish
Title of host publicationBritish Machine Vision Conference, BMVC 2009 - Proceedings
PublisherBritish Machine Vision Association, BMVA
ISBN (Print)1901725391, 9781901725391
DOIs
StatePublished - 2009
Event2009 20th British Machine Vision Conference, BMVC 2009 - London, United Kingdom
Duration: 7 Sep 200910 Sep 2009

Publication series

NameBritish Machine Vision Conference, BMVC 2009 - Proceedings

Conference

Conference2009 20th British Machine Vision Conference, BMVC 2009
Country/TerritoryUnited Kingdom
CityLondon
Period7/09/0910/09/09

Fingerprint

Dive into the research topics of 'Multiple one-shots for utilizing class label information'. Together they form a unique fingerprint.

Cite this