Synthetic Data for the Mitigation of Demographic Biases in Face Recognition

Pietro Melzi,Christian Rathgeb,Ruben Tolosana,Ruben Vera-Rodriguez,Aythami Morales, Dominik Lawatsch, Florian Domin, Maxim Schaubert

2023 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS, IJCB(2023)

引用 0|浏览2
暂无评分
摘要
This study investigates the possibility of mitigating the demographic biases that affect face recognition technologies through the use of synthetic data. Demographic biases have the potential to impact individuals from specific demographic groups, and can be identified by observing disparate performance of face recognition systems across demographic groups. They primarily arise from the unequal representations of demographic groups in the training data. In recent times, synthetic data have emerged as a solution to some problems that affect face recognition systems. In particular, during the generation process it is possible to specify the desired demographic and facial attributes of images, in order to control the demographic distribution of the synthesized dataset, and fairly represent the different demographic groups. We propose to fine-tune with synthetic data existing face recognition systems that present some demographic biases. We use synthetic datasets generated with GANDiffFace, a novel framework able to synthesize datasets for face recognition with controllable demographic distribution and realistic intra-class variations. We consider multiple datasets representing different demographic groups for training and evaluation. Also, we fine-tune different face recognition systems, and evaluate their demographic fairness with different metrics. Our results support the proposed approach and the use of synthetic data to mitigate demographic biases in face recognition.
更多
查看译文
关键词
Face Recognition,Demographic Bias,Training Data,System Performance,Demographic Groups,Real Variables,Demographic Distribution,Intra-class Variance,Demographic Attributes,Facial Recognition Technology,Specific Demographic Groups,Training Dataset,Image Quality,Test Dataset,Asian Populations,Large-scale Datasets,Generative Adversarial Networks,Diffusion Model,Original System,Real-world Datasets,Algorithmic Bias,Balanced Dataset,Asian Subjects,Fine-tuning Process,Evaluation Dataset,Gini Coefficient,Test Subset,Gender Balance
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要