Balancing Beyond Discrete Categories: Continuous Demographic Labels for Fair Face Recognition
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_ | 1866915330212757504 |
|---|---|
| author | Neto, Pedro C. Damer, Naser Cardoso, Jaime S. Sequeira, Ana F. |
| author_facet | Neto, Pedro C. Damer, Naser Cardoso, Jaime S. Sequeira, Ana F. |
| contents | Bias has been a constant in face recognition models. Over the years, researchers have looked at it from both the model and the data point of view. However, their approach to mitigation of data bias was limited and lacked insight on the real nature of the problem. Here, in this document, we propose to revise our use of ethnicity labels as a continuous variable instead of a discrete value per identity. We validate our formulation both experimentally and theoretically, showcasing that not all identities from one ethnicity contribute equally to the balance of the dataset; thus, having the same number of identities per ethnicity does not represent a balanced dataset. We further show that models trained on datasets balanced in the continuous space consistently outperform models trained on data balanced in the discrete space. We trained more than 65 different models, and created more than 20 subsets of the original datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01532 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Balancing Beyond Discrete Categories: Continuous Demographic Labels for Fair Face Recognition Neto, Pedro C. Damer, Naser Cardoso, Jaime S. Sequeira, Ana F. Computer Vision and Pattern Recognition Bias has been a constant in face recognition models. Over the years, researchers have looked at it from both the model and the data point of view. However, their approach to mitigation of data bias was limited and lacked insight on the real nature of the problem. Here, in this document, we propose to revise our use of ethnicity labels as a continuous variable instead of a discrete value per identity. We validate our formulation both experimentally and theoretically, showcasing that not all identities from one ethnicity contribute equally to the balance of the dataset; thus, having the same number of identities per ethnicity does not represent a balanced dataset. We further show that models trained on datasets balanced in the continuous space consistently outperform models trained on data balanced in the discrete space. We trained more than 65 different models, and created more than 20 subsets of the original datasets. |
| title | Balancing Beyond Discrete Categories: Continuous Demographic Labels for Fair Face Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.01532 |