通过调整皮肤病条件分布差异来缩小 AI 泛化差距
图像与视频处理
2024-02-27 v1 计算机视觉与模式识别
机器学习
摘要
最近，人工智能（AI）算法在临床照片中对皮肤病条件进行分类的能力取得了很大进展。然而，关于这些算法在真实世界环境中的鲁棒性几乎没有了解。理解并克服这些限制将使能够开发出可在各种临床环境中辅助皮肤病诊断的通用 AI。在本retrospective研究中，我们展示了皮肤病分布差异（而非人口学特征或图像获取方式）是当 AI 算法在来自以前未见来源的数据上进行评估时，错误主要来源。我们演示了一系列步骤来缩小这种泛化差距，所需信息关于新来源逐渐增加，从皮肤病分布到针对训练期间较少看到的少数数据丰富化的训练数据。我们的结果还表明，端到端微调与仅对冻结嵌入模型顶部的分类层进行微调的性能相当。我们的ethods can inform the adaptation of AI algorithms to new settings, based on the information and resources available.
引用
@article{arxiv.2402.15566,
title = {Closing the AI generalization gap by adjusting for dermatology condition distribution differences across clinical settings},
author = {Rajeev V. Rikhye and Aaron Loh and Grace Eunhae Hong and Preeti Singh and Margaret Ann Smith and Vijaytha Muralidharan and Doris Wong and Rory Sayres and Michelle Phung and Nicolas Betancourt and Bradley Fong and Rachna Sahasrabudhe and Khoban Nasim and Alec Eschholz and Basil Mustafa and Jan Freyberg and Terry Spitz and Yossi Matias and Greg S. Corrado and Katherine Chou and Dale R. Webster and Peggy Bui and Yuan Liu and Yun Liu and Justin Ko and Steven Lin},
journal= {arXiv preprint arXiv:2402.15566},
year = {2024}
}