Self-supervised learning through the eyes of a child

2020/07/31 by A. Emin Orhan, Orhan, A. Emin, Vaibhav V. Gupta +3 · 5 citations
Psychology · Social Sciences · #Child and Animal Learning Development #Computer Vision and Pattern Recognition (cs.CV) #Education and Critical Thinking Development #FOS: Computer and information sciences #Innovative Teaching and Learning Methods #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)

paper · pdf · doi:10.48550/arxiv.2007.16189

openalex publication_date 2020/07/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Within months of birth, children develop meaningful expectations about the world around them. How much of this early knowledge can be explained through generic learning mechanisms applied to sensory data, and how much of it requires more substantive innate inductive biases? Addressing this fundamental question in its full generality is currently infeasible, but we can hope to make real progress in more narrowly defined domains, such as the development of high-level visual categories, thanks to improvements in data collecting technology and recent progress in deep learning. In this paper, our goal is precisely to achieve such progress by utilizing modern self-supervised deep learning methods and a recent longitudinal, egocentric video dataset recorded from the perspective of three young children (Sullivan et al., 2020). Our results demonstrate the emergence of powerful, high-level visual representations from developmentally realistic natural videos using generic self-supervised learning objectives.

Citations

• Simple memory: a theory for archicortex
• Slow Feature Analysis: Unsupervised Learning of Invariances
• A Simple Framework for Contrastive Learning of Visual Representations
• Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs
• Improved Baselines with Momentum Contrastive Learning
• Self-Training With Noisy Student Improves ImageNet Classification
• Momentum Contrast for Unsupervised Visual Representation Learning

Cited by

• A Knowledge-Based Language Model: Deducing Grammatical Knowledge in a Multi-Agent Language Acquisition Simulation
• Learning to See Through a Baby's Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machines
• Do Blind Spots Matter for Word-Referent Mapping? A Computational Study with Infant Egocentric Video
• Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception
• Partial success in closing the gap between human and machine vision

Related

• Self-supervised learning of video representations from a child's perspective
• Learning high-level visual representations from a child's perspective without strong inductive biases
• The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences
• Learning to See Through a Baby's Eyes: Early Visual Diets Enable Robust Visual Intelligence in Humans and Machines
• A Computational Account Of Self-Supervised Visual Learning From Egocentric Object Play