Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domains

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lin, Yumeng, Li, Dong, Wu, Xintao, Shao, Minglai, Zhao, Xujiang, Chen, Zhong, Zhao, Chen
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916927675301888
author Lin, Yumeng
Li, Dong
Wu, Xintao
Shao, Minglai
Zhao, Xujiang
Chen, Zhong
Zhao, Chen
author_facet Lin, Yumeng
Li, Dong
Wu, Xintao
Shao, Minglai
Zhao, Xujiang
Chen, Zhong
Zhao, Chen
contents Ensuring fairness and robustness in machine learning models remains a challenge, particularly under domain shifts. We present Face4FairShifts, a large-scale facial image benchmark designed to systematically evaluate fairness-aware learning and domain generalization. The dataset includes 100,000 images across four visually distinct domains with 39 annotations within 14 attributes covering demographic and facial features. Through extensive experiments, we analyze model performance under distribution shifts and identify significant gaps. Our findings emphasize the limitations of existing related datasets and the need for more effective fairness-aware domain adaptation techniques. Face4FairShifts provides a comprehensive testbed for advancing equitable and reliable AI systems. The dataset is available online at https://meviuslab.github.io/Face4FairShifts/.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00658
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domains
Lin, Yumeng
Li, Dong
Wu, Xintao
Shao, Minglai
Zhao, Xujiang
Chen, Zhong
Zhao, Chen
Computer Vision and Pattern Recognition
Computers and Society
Machine Learning
Ensuring fairness and robustness in machine learning models remains a challenge, particularly under domain shifts. We present Face4FairShifts, a large-scale facial image benchmark designed to systematically evaluate fairness-aware learning and domain generalization. The dataset includes 100,000 images across four visually distinct domains with 39 annotations within 14 attributes covering demographic and facial features. Through extensive experiments, we analyze model performance under distribution shifts and identify significant gaps. Our findings emphasize the limitations of existing related datasets and the need for more effective fairness-aware domain adaptation techniques. Face4FairShifts provides a comprehensive testbed for advancing equitable and reliable AI systems. The dataset is available online at https://meviuslab.github.io/Face4FairShifts/.
title Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domains
topic Computer Vision and Pattern Recognition
Computers and Society
Machine Learning
url https://arxiv.org/abs/2509.00658