比较孩子和神经网络在少量标注下学分类，发现学习机制差异大。
Feature, Alignment, and Supervision in Category Learning: A Comparative Approach with Children and Neural Networks
- 用相同数据条件对比儿童与CNN的少样本分类学习
- 孩子用1-3个标签就快速泛化，但受特征和对齐度影响大
- 模型随标签增多提升，但效果受特征结构和对齐度调节
理解人类与机器如何从稀疏数据中学习，是认知科学与机器学习的核心问题。采用跨物种公平设计，我们比较了儿童与卷积神经网络（CNN）在少样本半监督分类任务中的表现。两者在完全相同的条件下接触新类别：接收混合的已标注与未标注样本，同时变化标注比例（1/3/6个标签）、目标特征（大小、形状、图案）及感知对齐度（高/低）。结果发现，儿童能从极少数标签快速泛化，但表现出强烈的特征特异性偏差和对对齐度的敏感性；而CNN则呈现不同交互模式：增加标注能提升性能，但其效果受到特征结构和对齐度的调节。研究强调，人机比较必须在恰当条件下进行，重点应放在标注、特征结构与对齐之间的相互作用，而非仅看整体准确率。
原文摘要 · Abstract (English)
Understanding how humans and machines learn from sparse data is central to cognitive science and machine learning. Using a species-fair design, we compare children and convolutional neural networks (CNNs) in a few-shot semi-supervised category learning task. Both learners are exposed to novel object categories under identical conditions. Learners receive mixtures of labeled and unlabeled exemplars while we vary supervision (1/3/6 labels), target feature (size, shape, pattern), and perceptual alignment (high/low). We find that children generalize rapidly from minimal labels but show strong feature-specific biases and sensitivity to alignment. CNNs show a different interaction profile: added supervision improves performance, but both alignment and feature structure moderate the impact additional supervision has on learning. These results show that human-model comparisons must be drawn under the right conditions, emphasizing interactions among supervision, feature structure, and alignment rather than overall accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。