Toddler-Inspired Visual Object Learning

Bambach, S, Crandall, D J, Smith, L B and Yu, C (2018) Toddler-Inspired Visual Object Learning. In: Advances in Neural Information Processing Systems. Neural Information Processing Systems Foundation, CAN.

[img]
Preview
PDF (Published manuscript) - Published Version
Download (2MB) | Preview

Abstract

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.

Item Type: Book Section
Faculty \ School: Faculty of Social Sciences > School of Psychology
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 29 Nov 2018 12:30
Last Modified: 17 Mar 2020 13:33
URI: https://ueaeprints.uea.ac.uk/id/eprint/69089
DOI:

Actions (login required)

View Item View Item