婴儿通过少量重复视觉体验，就能快速分类物体。
A solution to generalized learning from small training sets found in infants repeated visual experiences of individual objects
- 分析婴儿日常用餐时的头戴相机图像，发现物体经验具有高度不均衡性。
- 高相似与高变异混合的图像结构支持在少量训练后泛化到新实例。
- 为人类和机器学习提供新机制启发，尤其适合小样本场景。
一岁婴儿能从极少数示例中快速形成并泛化类别。本研究基于87次用餐时段、14名婴儿的头戴相机图像数据，分析8个物体类别的日常视觉经验统计特征。结果显示，每位婴儿对特定物体的接触频率分布高度偏斜：少数物体被反复观察，其余则较少出现。图论分析揭示，同一类别的视觉经验呈现‘块状’结构——包含多个内部高相似、跨组高差异的互连簇。计算实验表明，人工构造的具备高低相似性交织的训练集，可在有限训练后实现对新实例的泛化。结果对类别识别及人机学习具有启示意义。
原文摘要 · Abstract (English)
One-year-old infants rapidly form and generalize categories from idiosyncratic experiences of very few exemplars of those categories. Here we provide evidence on the statistics of infants daily-life visual experiences for 8 object categories. Using a corpus of infant head-camera images recorded at mealtimes (87 mealtimes,14 infants), we measure the frequency of the unique instances of each category and the variability of the visual experiences within and across instances of the same category. The frequency distributions of instances for individual infants are highly skewed, containing many images of the same few objects along with fewer images of other instances. Graph theoretic measures of individual category experiences for individual children reveal a lumpy mix of high similarity and high variability, organized into multiple but interconnected clusters of high-similarity images. In computational experiments, we show that artificially created training sets characterized by an interconnected mix of high and low similarity support generalization to novel instances after limited training. We discuss implications for category recognition, and for learning more generally, by both humans and machines.
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。