通过引导扩散实现对极其稀有病理学类的改进尾部检测
计算机视觉与模式识别
2024-09-04 v1 机器学习
摘要
在现实医疗环境中，数据往往具有长尾分布，大多数样本集中在少数类别中，而稀有类别形成长尾，通常仅包含少量样本。这种分布 presents a significant challenge because rare conditions are critical to detect and difficult to classify due to limited data. In this paper, rather than attempting to classify rare classes, we aim to detect these as out-of-distribution data reliably. We leverage low-rank adaption (LoRA) and diffusion guidance to generate targeted synthetic data for the detection problem. We significantly improve the OOD detection performance on a challenging histopathological task with only ten samples per tail class without losing classification accuracy on the head classes.
引用
@article{arxiv.2409.01317,
title = {LoGex: Improved tail detection of extremely rare histopathology classes via guided diffusion},
author = {Maximilian Mueller and Matthias Hein},
journal= {arXiv preprint arXiv:2409.01317},
year = {2024}
}