Efficient Face Recognition Competition (EFaR-2023) Call for Papers

Call for competition participation  
IJCB 2023 
Efficient Face Recognition Competition (EFaR-2023)

 

Competition website: https://sites.google.com/view/ijcb-2023-efar/

 

IJCB2023 website: https://ijcb2023.ieee-biometrics.org/

----------------------------------------------------------------------

Facial recognition is currently used in our daily lives and in many
applications. This includes authorizing financial transfers with our
personal devices, logging into different devices and accounts,
performing an automatic border control, or even personalizing our
driving experience. Developing efficient biometric solutions is
essential to minimize the required computational costs, especially
when deployed on embedded and low-end devices. However, most of the
current face recognition systems use deep neural networks with extreme
number of trainable parameters. These systems are limited in their
application by the high computational effort required, whether because
of a shared resource environment of deployment devices, in which
computing capacity and battery are shared with other smart
applications, or because the requirement of instance decisions by the
user. Therefore, there is a great need for face recognition systems
that offer high performance at the lowest possible computational cost.
The aim of EFaR-2023 competition is to attract and showcase the latest
innovations in efficient and lightweight face recognition and to
motivate the development of novel techniques.  The competition will
look into two categories of models, each of which gets its own
ranking:

-              Models with up to 2 million Parameters

-              And models with 2-5 million parameters

In each category, the accuracy of the models will be the main deciding
factor, however, the ranking will also consider the required FLOPs and
the model size to take the real-time response possibility and limited
device memory into perspective.

----------------------------------------------------------------------

The top-3 ranked teams in each category will be invited as the
co-authors of the competition report paper (this will be extended in
case of a large number of competitive participants). The competition
summary paper will be submitted to the International Joint Conference
on Biometrics (IJCB) 2023.

----------------------------------------------------------------------

Schedule information under: https://sites.google.com/view/ijcb-2023-efar/

----------------------------------------------------------------------

Competition Organizers

 

Jan Niklas Kolf - Fraunhofer Institute for Computer Graphics Research
IGD, Germany and TU Darmstadt, Germany.

Fadi Boutros - Fraunhofer Institute for Computer Graphics Research
IGD, Germany.

Naser Damer - Fraunhofer Institute for Computer Graphics Research IGD,
Germany and TU Darmstadt, Germany.

 

----------------------------------------------------------------------
Best regards,
On behalf of the organizers,
Naser Damer
Smart Living & Biometric Technologies
Fraunhofer Institute for Computer Graphics Research IGD
Fraunhoferstr. 5  |  64283 Darmstadt  |  Germany Tel +49 6151 155-521
Fax +49 6151 155-499 | naser.damer@igd.fraunhofer.de  | www.igd.fraunhofer.de