This website requires JavaScript.

Dataset Distillation for Medical Dataset Sharing

Guang LiRen TogoTakahiro OgawaMiki Haseyama
Sep 2022
摘要
Sharing medical datasets between hospitals is challenging because of theprivacy-protection problem and the massive cost of transmitting and storingmany high-resolution medical images. However, dataset distillation cansynthesize a small dataset such that models trained on it achieve comparableperformance with the original large dataset, which shows potential for solvingthe existing medical sharing problems. Hence, this paper proposes a noveldataset distillation-based method for medical dataset sharing. Experimentalresults on a COVID-19 chest X-ray image dataset show that our method canachieve high detection performance even using scarce anonymized chest X-rayimages.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答