English(EN) When Does Small Data Work? Accuracy and Efficiency Trade-offs Between Tabular Foundation Models and Conventional Methods for Crowd-State Classification at Hajj and Umrah

表格基础模型与传统机器学习在人群分类中的对比

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-07 04:00

一篇新的研究论文探讨了表格基础模型与传统机器学习方法在人群状态分类方面的有效性，特别是在标记数据有限的情况下。该研究聚焦于朝觐和副朝期间的人群监测，发现当标签极度稀缺时，基础模型表现更好。然而，随着可用标签数量的增加，经过调优的传统模型变得更准确，并超越了基础模型，尤其是在处理复杂的几何目标时。研究还强调了效率权衡，指出基础模型避免了传统方法显著的调优成本，但需要为每次预测重新处理上下文。 AI

影响为在数据有限的任务中选择基础模型与传统机器学习提供了见解，这对于专业领域的AI从业者具有参考价值。

排序理由关于机器学习方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · AlJawharh S. AlOtaibi, Mohamed Eltahir, Jude AlSubaie · 2026-07-07 04:00

When Does Small Data Work? Accuracy and Efficiency Trade-offs Between Tabular Foundation Models and Conventional Methods for Crowd-State Classification at Hajj and Umrah

arXiv:2607.04013v1 Announce Type: cross Abstract: Learning from few labeled examples is a central challenge in tabular machine learning, and it becomes the binding constraint in domains where labeling is costly, such as crowd monitoring during Hajj and Umrah. Tabular foundation m…

报道来源 [1]

When Does Small Data Work? Accuracy and Efficiency Trade-offs Between Tabular Foundation Models and Conventional Methods for Crowd-State Classification at Hajj and Umrah

相关实体

相关话题