학술논문
FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data
Document Type
Conference
Author
Melzi, Pietro; Tolosana, Ruben; Vera-Rodriguez, Ruben; Kim, Minchul; Rathgeb, Christian; Liu, Xiaoming; DeAndres-Tame, Ivan; Morales, Aythami; Fierrez, Julian; Ortega-Garcia, Javier; Zhao, Weisong; Zhu, Xiangyu; Yan, Zheyu; Zhang, Xiao-Yu; Wu, Jinlin; Lei, Zhen; Tripathi, Suvidha; Kothari, Mahak; Zama, Md Haider; Deb, Debayan; Biesseck, Bernardo; Vidal, Pedro; Granada, Roger; Fickel, Guilherme; Fuhr, Gustavo; Menotti, David; Unnervik, Alexander; George, Anjith; Ecabert, Christophe; Shahreza, Hatef Otroshi; Rahimi, Parsa; Marcel, Sebastien; Sarridis, Ioannis; Koutlis, Christos; Baltsou, Georgia; Papadopoulos, Symeon; Diou, Christos; Di Domenico, Nicolo; Borghi, Guido; Pellegrini, Lorenzo; Mas-Candela, Enrique; Sanchez-Perez, Angela; Atzori, Andrea; Fenu, Gianni; Boutros, Fadi; Marras, Mirko; Damer, Naser
Source
2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) WACVW Applications of Computer Vision Workshops (WACVW), 2024 IEEE/CVF Winter Conference on. :892-901 Jan, 2024
Subject
Language
ISSN
2690-621X
Abstract
Despite the widespread adoption of face recognition technology around the world, and its remarkable performance on current benchmarks, there are still several challenges that must be covered in more detail. This paper offers an overview of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at WACV 2024. This is the first international challenge aiming to explore the use of synthetic data in face recognition to address existing limitations in the technology. Specifically, the FRCSyn Challenge targets concerns related to data privacy issues, demographic biases, generalization to unseen scenarios, and performance limitations in challenging scenarios, including significant age disparities between enrollment and testing, pose variations, and occlusions. The results achieved in the FRCSyn Challenge, together with the proposed benchmark, contribute significantly to the application of synthetic data to improve face recognition technology.