SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

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 infl

Read original source ↗ Open in workspace

recordType

paper

region

Global