A Responsible Face Recognition Approach for Small and Mid-Scale Systems Through Personalized Neural Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913859566043136 |
|---|---|
| author | Groß, Sebastian Heindorf, Stefan Terhörst, Philipp |
| author_facet | Groß, Sebastian Heindorf, Stefan Terhörst, Philipp |
| contents | Traditional face recognition systems rely on extracting fixed face representations, known as templates, to store and verify identities. These representations are typically generated by neural networks that often lack explainability and raise concerns regarding fairness and privacy. In this work, we propose a novel model-template (MOTE) approach that replaces vector-based face templates with small personalized neural networks. This design enables more responsible face recognition for small and medium-scale systems. During enrollment, MOTE creates a dedicated binary classifier for each identity, trained to determine whether an input face matches the enrolled identity. Each classifier is trained using only a single reference sample, along with synthetically balanced samples to allow adjusting fairness at the level of a single individual during enrollment. Extensive experiments across multiple datasets and recognition systems demonstrate substantial improvements in fairness and particularly in privacy. Although the method increases inference time and storage requirements, it presents a strong solution for small- and mid-scale applications where fairness and privacy are critical. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19920 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Responsible Face Recognition Approach for Small and Mid-Scale Systems Through Personalized Neural Networks Groß, Sebastian Heindorf, Stefan Terhörst, Philipp Computer Vision and Pattern Recognition Artificial Intelligence Traditional face recognition systems rely on extracting fixed face representations, known as templates, to store and verify identities. These representations are typically generated by neural networks that often lack explainability and raise concerns regarding fairness and privacy. In this work, we propose a novel model-template (MOTE) approach that replaces vector-based face templates with small personalized neural networks. This design enables more responsible face recognition for small and medium-scale systems. During enrollment, MOTE creates a dedicated binary classifier for each identity, trained to determine whether an input face matches the enrolled identity. Each classifier is trained using only a single reference sample, along with synthetically balanced samples to allow adjusting fairness at the level of a single individual during enrollment. Extensive experiments across multiple datasets and recognition systems demonstrate substantial improvements in fairness and particularly in privacy. Although the method increases inference time and storage requirements, it presents a strong solution for small- and mid-scale applications where fairness and privacy are critical. |
| title | A Responsible Face Recognition Approach for Small and Mid-Scale Systems Through Personalized Neural Networks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2505.19920 |