AD-VAE: Adversarial Disentangling Variational Autoencoder
Sensors · 2025
DOI: 10.3390/s25051574 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Adson Silva und 1 weiteren Autor:innen. Beteiligte Einrichtung: Systems Engineering and Computer Science Program (PESC/COPPE/UFRJ), Federal University of Rio de Janeiro, Rio de Janeiro 21941-972, Brazil. Hauptthemen laut MEDLINE: Autoencoder, Automated Facial Recognition, Biometric Identification. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeicoamento de Pessoal de Nível Superior, Insituto Federal de Educação, Ciências e Tecnologia da Paraíba IFPB, Instituto Federal de Educação, Ciência e Tecnologia da Paraíba (IFPB).
Abstract (Originalsprache)
Face recognition (FR) is a less intrusive biometrics technology with various applications, such as security, surveillance, and access control systems. FR remains challenging, especially when there is only a single image per person as a gallery dataset and when dealing with variations like pose, illumination, and occlusion. Deep learning techniques have shown promising results in recent years using VAE and GAN, with approaches such as patch-VAE, VAE-GAN for 3D Indoor Scene Synthesis, and hybrid VAE-GAN models. However, in Single Sample Per Person Face Recognition (SSPP FR), the challenge of learning robust and discriminative features that preserve the subject’s identity persists. To address these issues, we propose a novel framework called AD-VAE, specifically for SSPP FR, using a combination of variational autoencoder (VAE) and Generative Adversarial Network (GAN) techniques. The proposed AD-VAE framework is designed to learn how to build representative identity-preserving prototypes from both controlled and wild datasets, effectively handling variations like pose, illumination, and occlusion. The method uses four networks: an encoder and decoder similar to VAE, a generator that receives the encoder output plus noise to generate an identity-preserving prototype, and a discriminator that operates as a multi-task network. AD-VAE outperforms all tested state-of-the-art face recognition techniques, demonstrating its robustness. The proposed framework achieves superior results on four controlled benchmark datasets—AR, E-YaleB, CAS-PEAL, and FERET—with recognition rates of 84.9%, 94.6%, 94.5%, and 96.0%, respectively, and achieves remarkable performance on the uncontrolled LFW dataset, with a recognition rate of 99.6%. The AD-VAE framework shows promising potential for future research and real-world applications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Systems Engineering and Computer Science Program (PESC/COPPE/UFRJ), Federal University of Rio de Janeiro, Rio de Janeiro 21941-972, Brazil.
ORCID-Profile: Adson Silva
Förderung
- Coordenação de Aperfeicoamento de Pessoal de Nível Superior
- Insituto Federal de Educação, Ciências e Tecnologia da Paraíba IFPB
- Instituto Federal de Educação, Ciência e Tecnologia da Paraíba (IFPB)
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Zitieren
APA
Silva, A., & Farias, R. (2025). AD-VAE: Adversarial Disentangling Variational Autoencoder. Sensors. https://doi.org/10.3390/s25051574
Vancouver
Silva A, Farias R. AD-VAE: Adversarial Disentangling Variational Autoencoder. Sensors. 2025. doi:10.3390/s25051574
BibTeX
@article{Silva2025,
author = {Silva, Adson and Farias, Ricardo},
title = {AD-VAE: Adversarial Disentangling Variational Autoencoder},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25051574}
}
EUVIMED