Toddler-Inspired Visual Object Learning
Toddler-Inspired Visual Object Learning
复制标题
受幼儿启发的视觉对象学习
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Chen Yu
中科院分区：
文献类型：
--
作者：
S. Bambach;David J. Crandall;Linda B. Smith;Chen Yu
现实世界的学习系统在他们可以收集和考虑的训练数据集的质量和数量上有实际的限制。一个系统应该如何选择一个可能的训练样本的子集，仍然允许学习准确的，可推广的模型？为了帮助解决这个问题，我们从一个高效的实用学习系统中汲取灵感：人类儿童。使用头戴式摄像机，眼睛注视跟踪器和中央凹视觉模型，我们收集了第一人称（自我中心）图像，这些图像代表了幼儿视觉系统在日常自然学习环境中收集的“训练数据”的高度准确近似。我们使用最先进的计算机视觉学习模型（卷积神经网络）来帮助描述这些数据的结构，并发现儿童数据产生的对象模型明显优于成年人在完全相同的环境中所经历的以自我为中心的数据。通过使用CNN作为建模工具来研究子数据的属性，可以实现这种快速学习，我们发现子数据表现出质量和多样性的独特组合，不仅有许多类似的大型高质量对象视图，而且还有更多数量和多样性的稀有视图。这种分析儿童使用的视觉“训练数据”的新方法不仅可以揭示改善机器学习的见解，还可以提出新的实验工具，以更好地理解发展心理学中的婴儿学习。
Real-world learning systems have practical limitations on the quality and quantity of the training datasets that they can collect and consider. How should a system go about choosing a subset of the possible training examples that still allows for learning accurate, generalizable models? To help address this question, we draw inspiration from a highly efficient practical learning system: the human child. Using head-mounted cameras, eye gaze trackers, and a model of foveated vision, we collected first-person (egocentric) images that represents a highly accurate approximation of the "training data" that toddlers' visual systems collect in everyday, naturalistic learning contexts. We used state-of-the-art computer vision learning models (convolutional neural networks) to help characterize the structure of these data, and found that child data produce significantly better object models than egocentric data experienced by adults in exactly the same environment. By using the CNNs as a modeling tool to investigate the properties of the child data that may enable this rapid learning, we found that child data exhibit a unique combination of quality and diversity, with not only many similar large, high-quality object views but also a greater number and diversity of rare views. This novel methodology of analyzing the visual "training data" used by children may not only reveal insights to improve machine learning, but also may suggest new experimental tools to better understand infant learning in developmental psychology.
影响因子：
3.8
作者：
Smith LB;Slone LK
通讯作者：
Slone LK
手眼协调预测共同注意力。
影响因子：
4.6
作者：
Yu,Chen;Smith,LindaB
通讯作者：
Smith,LindaB
DOI：
10.1037/xge0000129
发表时间：
2016-01
期刊：
Journal of experimental psychology. General
影响因子：
--
作者：
Greene MR;Baldassano C;Esteva A;Beck DM;Fei-Fei L
通讯作者：
Fei-Fei L