Treffer: Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data

Title:
Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data
Authors:
DeAndres-Tame, Ivan, Tolosana, Ruben, Melzi, Pietro, Vera-Rodriguez, Ruben, Kim, Minchul, Rathgeb, Christian, Liu, Xiaoming, Morales, Aythami, Fierrez, Julian, Ortega-Garcia, Javier, Zhong, Zhizhou, Huang, Yuge, Mi, Yuxi, Ding, Shouhong, Zhou, Shuigeng, He, Shuai, Fu, Lingzhi, Cong, Heng, Zhang, Rongyu, Xiao, Zhihong, Smirnov, Evgeny, Pimenov, Anton, Grigorev, Aleksei, Timoshenko, Denis, Asfaw, Kaleb Mesfin, Yaw Low, Cheng, Liu, Hao, Wang, Chuyi, Zuo, Qing, He, Zhixiang, Shahreza, Hatef Otroshi, George, Anjith, Unnervik, Alexander, Rahimi, Parsa, Marcel, Sébastien, Neto, Pedro C., Huber, Marco, Kolf, Jan Niklas, Damer, Naser, Boutros, Fadi, Cardoso, Jaime S., Sequeira, Ana F., Atzori, Andrea, Fenu, Gianni, Marras, Mirko, Štruc, Vitomir, Yu, Jiang, Li, Zhangjie, Li, Jichun, Zhao, Weisong, Lei, Zhen, Zhu, Xiangyu, Zhang, Xiao-Yu, Biesseck, Bernardo, Vidal, Pedro, Coelho, Luiz, Granada, Roger, Menotti, David
Publication Year:
2024
Collection:
Publikationsdatenbank der Fraunhofer-Gesellschaft
Subject Terms:
Branche: Information Technology, Research Line: Computer vision (CV), Research Line: Human computer interaction (HCI), Research Line: Machine learning (ML), LTA: Interactive decision-making support and assistance systems, LTA: Machine intelligence, algorithms, and data structures (incl. semantics), LTA: Generation, capture, processing, and output of images and 3D models, Biometrics, Face recognition, Machine learning, ATHENE
Document Type:
Konferenz conference object
Language:
English
Relation:
Conference on Computer Vision and Pattern Recognition Workshops 2024; Face Recognition Challenge in the Era of Synthetic Data 2024; #PLACEHOLDER_PARENT_METADATA_VALUE#; IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024. Proceedings; Next Generation Biometric Systems; https://publica.fraunhofer.de/handle/publica/475939
DOI:
10.1109/CVPRW63382.2024.00323
Availability:
https://publica.fraunhofer.de/handle/publica/475939
https://doi.org/10.1109/CVPRW63382.2024.00323
Accession Number:
edsbas.25F3EEA8
Database:
BASE

Weitere Informationen

3173 ; 3183 ; Synthetic data is gaining increasing relevance for train ing machine learning models. This is mainly motivated due to several factors such as the lack of real data and intra class variability, time and errors produced in manual la beling, and in some cases privacy concerns, among others. This paper presents an overview of the 2nd edition of the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn) organized at CVPR 2024. FRCSyn aims to in vestigate the use of synthetic data in face recognition to ad dress current technological limitations, including data pri vacy concerns, demographic biases, generalization to novel scenarios, and performance constraints in challenging sit uations such as aging, pose variations, and occlusions. Un like the 1st edition, in which synthetic data from DCFace and GANDiffFace methods was only allowed to train face recognition systems, in this 2nd edition we propose new sub tasks that allow participants to explore novel face genera tive methods. The outcomes of the 2nd FRCSyn Challenge, along with the proposed experimental protocol and bench marking contribute significantly to the application of syn thetic data to face recognition.