English(EN) Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptions

少样本学习的评估协议可能高估模型性能

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-11 04:00

一篇新论文批判性地审视了少样本学习评估背后的假设，特别是预训练模型在大型辅助数据集上的常见做法。研究人员发现，即使在目标样本类别不重叠但属于同一视觉域的情况下进行预训练，也会显著高估性能。研究表明，对于稀缺的目标域数据，域外预训练更为现实，并且令人惊讶的是，无标签增强策略可以取得与监督域外预训练相当的结果。该论文主张放弃将域内预训练作为默认评估协议，以更好地反映现实世界场景。 AI

影响挑战了少样本学习的标准评估方法，可能导致更现实的性能评估，并影响未来的模型开发。

排序理由学术论文发表在arXiv上，详细阐述了对机器学习评估协议的批判性审视。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文发表在arXiv上，详细阐述了对机器学习评估协议的批判性审视。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Alejandro Galan-Cuenca, Marcelo Saval-Calvo, Antonio Javier Gallego · 2026-09-11 04:00

我们真的在做少样本学习吗？对预训练假设的批判性审视

arXiv:2609.10851v1 Announce Type: cross Abstract: Few-shot learning is commonly evaluated under protocols that pre-train a model on a large auxiliary set whose classes are disjoint from the target episodes yet drawn from the same visual domain. This paper examines whether such pr…

本文如何被排名

报道来源 [1]

我们真的在做少样本学习吗？对预训练假设的批判性审视

相关实体

相关话题