Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Publicações

Publicações por Pedro David Carneiro

2024

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

Autores
Tame, ID; Tolosana, R; Melzi, P; Rodríguez, RV; Kim, M; Rathgeb, C; Liu, X; Morales, A; Fiérrez, J; Garcia, JO; Zhong, Z; Huang, Y; Mi, Y; Ding, S; Zhou, S; He, S; Fu, L; Cong, H; Zhang, R; Xiao, Z; Smirnov, E; Pimenov, A; Grigorev, A; Timoshenko, D; Asfaw, KM; Low, CY; Liu, H; Wang, C; Zuo, Q; He, Z; Shahreza, HO; George, A; Unnervik, A; Rahimi, P; Marcel, S; Neto, PC; Huber, M; Kolf, JN; Damer, N; Boutros, F; Cardoso, JS; Sequeira, AF; Atzori, A; Fenu, G; Marras, M; Struc, V; Yu, J; Li, Z; Li, J; Zhao, W; Lei, Z; Zhu, X; Zhang, XY; Biesseck, B; Vidal, P; Coelho, L; Granada, R; Menotti, D;

Publicação
IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Workshops, Seattle, WA, USA, June 17-18, 2024

Abstract

2024

Massively Annotated Datasets for Assessment of Synthetic and Real Data in Face Recognition

Autores
Neto, PC; Mamede, RM; Albuquerque, C; Gonçalves, T; Sequeira, AF;

Publicação
2024 IEEE 18TH INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, FG 2024

Abstract
Face recognition applications have grown in parallel with the size of datasets, complexity of deep learning models and computational power. However, while deep learning models evolve to become more capable and computational power keeps increasing, the datasets available are being retracted and removed from public access. Privacy and ethical concerns are relevant topics within these domains. Through generative artificial intelligence, researchers have put efforts into the development of completely synthetic datasets that can be used to train face recognition systems. Nonetheless, the recent advances have not been sufficient to achieve performance comparable to the state-of-the-art models trained on real data. To study the drift between the performance of models trained on real and synthetic datasets, we leverage a massive attribute classifier (MAC) to create annotations for four datasets: two real and two synthetic. From these annotations, we conduct studies on the distribution of each attribute within all four datasets. Additionally, we further inspect the differences between real and synthetic datasets on the attribute set. When comparing through the Kullback-Leibler divergence we have found differences between real and synthetic samples. Interestingly enough, we have verified that while real samples suffice to explain the synthetic distribution, the opposite could not be further from being true.

  • 5
  • 5