BriefGPT.xyz
Jan, 2024
无需人口统计实现皮肤疾病诊断的公平性
Achieve Fairness without Demographics for Dermatological Disease Diagnosis
HTML
PDF
Ching-Hao Chiu, Yu-Jen Chen, Yawen Wu, Yiyu Shi, Tsung-Yi Ho
TL;DR
在医学图像诊断中,公平性变得越来越重要。本文提出了一种方法,在测试阶段实现对敏感属性的公平预测,而无需在训练过程中使用此类信息,并通过增强模型特征和规范特征的纠缠关系来提高公平性和准确性。实验结果表明,在两个皮肤病数据集中,该方法能够提高分类的公平性。
Abstract
In
medical image diagnosis
,
fairness
has become increasingly crucial. Without bias mitigation, deploying unfair AI would harm the interests of the underprivileged population and potentially tear society apart. Re
→