-
[pdf]
[arXiv]
[bibtex]@InProceedings{Deandres-Tame_2024_CVPR, author = {Deandres-Tame, Ivan and Tolosana, Ruben and Melzi, Pietro and Vera-Rodriguez, Ruben and Kim, Minchul and Rathgeb, Christian and Liu, Xiaoming and Morales, Aythami and Fierrez, Julian and Ortega-Garcia, Javier and Zhong, Zhizhou and Huang, Yuge and Mi, Yuxi and Ding, Shouhong and Zhou, Shuigeng and He, Shuai and Fu, Lingzhi and Cong, Heng and Zhang, Rongyu and Xiao, Zhihong and Smirnov, Evgeny and Pimenov, Anton and Grigorev, Aleksei and Timoshenko, Denis and Asfaw, Kaleb Mesfin and Low, Cheng Yaw and Liu, Hao and Wang, Chuyi and Zuo, Qing and He, Zhixiang and Shahreza, Hatef Otroshi and George, Anjith and Unnervik, Alexander and Rahimi, Parsa and Marcel, S\'ebastien and Neto, Pedro C. and Huber, Marco and Kolf, Jan Niklas and Damer, Naser and Boutros, Fadi and Cardoso, Jaime S. and Sequeira, Ana F. and Atzori, Andrea and Fenu, Gianni and Marras, Mirko and \v{S}truc, Vitomir and Yu, Jiang and Li, Zhangjie and Li, Jichun and Zhao, Weisong and Lei, Zhen and Zhu, Xiangyu and Zhang, Xiao-Yu and Biesseck, Bernardo and Vidal, Pedro and Coelho, Luiz and Granada, Roger and Menotti, David}, title = {Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {3173-3183} }
Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data
Abstract
Synthetic data is gaining increasing relevance for training 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 labeling 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 investigate the use of synthetic data in face recognition to address current technological limitations including data privacy concerns demographic biases generalization to novel scenarios and performance constraints in challenging situations such as aging pose variations and occlusions. Unlike 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 generative methods. The outcomes of the 2nd FRCSyn Challenge along with the proposed experimental protocol and benchmarking contribute significantly to the application of synthetic data to face recognition.
Related Material