loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Joel Z. Leibo ; Qianli Liao and Tomaso Poggio

Affiliation: MIT, United States

Keyword(s): Invariance, Face Identification, Same-different Matching, Labeled Faces in the Wild, Synthetic Data.

Abstract: Unconstrained face recognition remains a challenging computer vision problem despite recent exceptionally high results ( ~ 95% accuracy) on the current gold standard evaluation dataset: Labeled Faces in the Wild (LFW). We offer a decomposition of the unconstrained problem into subtasks based on the idea that invariance to identity-preserving transformations is the crux of recognition. Each of the subtasks in the Subtasks of Unconstrained Face Recognition (SUFR) challenge consists of a same-different face-matching problem on a set of 400 individual synthetic faces rendered so as to isolate a specific transformation or set of transformations. We characterized the performance of 9 different models (8 previously published) on each of the subtasks. One notable finding was that the HMAX-C2 feature was not nearly as clutter-resistant as had been suggested by previous publications. Next we considered LFW and argued that it is too easy of a task to continue to be regarded as a measure of prog ress on unconstrained face recognition. In particular, strong performance on LFW requires almost no invariance, yet it cannot be considered a fair approximation of the outcome of a detection --> alignment pipeline since it does not contain the kinds of variability that realistic alignment systems produce when working on non-frontal faces. We offer a new, more difficult, natural image dataset: SUFR-in-the-Wild (SUFR-W), which we created using a protocol that was similar to LFW, but with a few differences designed to produce more need for transformation invariance. We present baseline results for eight different face recognition systems on the new dataset and argue that it is time to retire LFW and move on to more difficult evaluations for unconstrained face recognition. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 35.175.121.135

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Z. Leibo, J.; Liao, Q. and Poggio, T. (2014). Subtasks of Unconstrained Face Recognition. In Proceedings of the 9th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2014) - Volume 1: VISAPP; ISBN 978-989-758-004-8; ISSN 2184-4321, SciTePress, pages 113-121. DOI: 10.5220/0004694201130121

@conference{visapp14,
author={Joel {Z. Leibo}. and Qianli Liao. and Tomaso Poggio.},
title={Subtasks of Unconstrained Face Recognition},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2014) - Volume 1: VISAPP},
year={2014},
pages={113-121},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004694201130121},
isbn={978-989-758-004-8},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2014) - Volume 1: VISAPP
TI - Subtasks of Unconstrained Face Recognition
SN - 978-989-758-004-8
IS - 2184-4321
AU - Z. Leibo, J.
AU - Liao, Q.
AU - Poggio, T.
PY - 2014
SP - 113
EP - 121
DO - 10.5220/0004694201130121
PB - SciTePress