发表机构
University Institute for Computer Research, University of Alicante（阿利坎特大学计算机研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文批判性审视少样本学习预训练假设，通过系统比较不同预训练方式，发现域内预训练存在乐观偏差，并提出无标签策略与源选择策略以提升现实场景下的评估可靠性。
AI 中文摘要
少样本学习通常在一种协议下进行评估，该协议在一个大型辅助集上预训练模型，辅助集的类别与目标任务（episodes）的类别不相交，但来自相同的视觉域。本文考察了此类协议是否真正反映了低数据学习。我们系统地比较了无预训练、类不相交的域内预训练、有监督的域外预训练和无标签的域外预训练，跨越八个数据集、三种少样本架构和多种way-shot设置。我们的结果表明，仅类不相交不足以消除目标域数据的影响。域内预训练平均比无预训练提高33.41个百分点，而有监督的域外预训练则提高23.75个百分点，揭示了与域重叠相关的9.66个百分点的乐观偏差。尽管在目标域数据稀缺的应用中，域外预训练更为现实，但其有效性强烈依赖于源域和目标域之间的兼容性。我们进一步表明，有标签的源数据并非严格必需，一种基于增强的无标签策略平均增益达到27.71个百分点，与有监督的域外预训练的27.97个百分点非常接近。最后，我们引入了一种基于描述符的源选择策略，在预训练前估计源域的适用性，与最优选择（oracle selection）的中位差距仅为1.37个百分点。这些发现强调需要超越域内预训练作为默认的少样本评估协议，因为在目标域数据稀缺的现实场景中，它可能高估性能。
英文摘要
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 protocols truly reflect low-data learning. We systematically compare no pre-training, class-disjoint in-domain pre-training, supervised out-of-domain pre-training, and label-free out-of-domain pre-training across eight datasets, three few-shot architectures, and multiple way-shot settings. Our results show that class disjointness alone is insufficient to remove the influence of target-domain data. In-domain pre-training improves over no pre-training by 33.41 percentage points on average, whereas supervised out-of-domain pre-training yields 23.75 percentage points, revealing a 9.66-point optimistic bias associated with domain overlap. Although out-of-domain pre-training is more realistic in applications where target-domain data are scarce, its effectiveness depends strongly on the compatibility between source and target domains. We further show that labeled source data are not strictly required, with an augmentation-based label-free strategy reaching an average gain of 27.71 percentage points and closely matching supervised out-of-domain pre-training at 27.97 percentage points. Finally, we introduce a descriptor-based source-selection strategy that estimates source-domain suitability before pre-training, reaching a median gap of only 1.37 percentage points to oracle selection. These findings highlight the need to move beyond in-domain pre-training as the default few-shot evaluation protocol, since it can overestimate performance in realistic scenarios where target-domain data are scarce.
