返回全部动态
深度学习图像分类器超参数优化的交叉验证方法比较研究
原标题：On Cross-Validation for Hyperparameter Optimization of Deep Learning Image Classifiers
AI 摘要
该研究比较了三种超参数优化协议（固定留出法、重洗留出法和5折交叉验证）在深度学习图像分类器中的性能估计误差。在医学影像数据集上，交叉验证在所有评估中均优于留出法，尤其在样本量较小时优势明显；在自然图像数据集上，三种协议差异不大。研究建议在计算资源允许时，小样本医学图像分类应采用基于交叉验证的超参数优化。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
On Cross-Validation for Hyperparameter Optimization of Deep Learning Image Classifiers Abstract Hyperparameter optimization (HPO) can materially affect the performance of deep learning (DL) image classifiers, but there is little empirical guidance on how to derive the validation signal that drives it, especially for the small sample sizes common in fields such as medical imaging. We compared three HPO protocols in terms of absolute performance-estimation error (AEE; the absolute difference betwe
发布时间：2026-08-18 12:00
抓取时间：2026-08-18 12:36
来源机构：arXiv