Toddlers’ Active Gaze Behavior Supports Self‐Supervised Object Learning
4 affiliations
- 1Frankfurt Institute for Advanced Studies Frankfurt Hessen Germany
- 2Xidian‐FIAS International Joint Research Center Frankfurt Hessen Germany
- 3Department of Psychology Center for Perceptual Systems University of Texas at Austin Austin Texas USA
- 4Department of Psychology University of California San Diego California USA
Abstract
Toddlers learn to recognize objects from different viewpoints with almost no supervision. During this learning, they execute frequent eye and head movements that shape their visual experience. It is presently unclear if and how these behaviors contribute to toddlers' emerging object recognition abilities. To answer this question, we here combine head-mounted eye tracking during dyadic play with unsupervised machine learning. We approximate toddlers' central visual field experience by cropping image regions from a head-mounted camera centered on the current gaze location estimated via eye tracking. This visual stream feeds a neural network model, which uses a biologically plausible unsupervised learning objective. Our experiments demonstrate that a few minutes of such first-person experience suffice to learn strong object representations permitting invariant object recognition. Importantly, by simulating alternative gaze behaviors we show that toddlers' eye movement patterns play a crucial role in this. Our analysis also reveals that the limited size of the central visual field where visual acuity is high plays an important role for successful learning. Together, this highlights the benefits of temporally structured visual experience arising from toddlers' natural interactions with objects. SUMMARY: We combine recordings of toddlers' first-person central visual field experience with biologically inspired self-supervised learning algorithms to model toddlers' development of invariant object recognition. Just a few minutes of toddlers' central visual field experience captured with head-mounted eye tracking suffice to learn strong object representations. Simulated alternative gaze behaviors produce weaker representations, demonstrating the importance of toddlers' active gaze strategies for learning. Our results emphasize the importance of toddlers' eye movements for learning object representations.
Related
- ABEL: an active-learning behavior estimation and labeling platform
- Transient feedforward communication between somatosensory and premotor cortex supports goal-directed behavior
- High-dimensional hippocampus representation facilitates learning of low-dimensional abstract representation and supports generalization
- Learning from Error Predictions Rather Than Prediction Errors: A Perspective on Self-Supervised Learning in the Brain
- Exploring noise in TCR specificity data through supervised learning
BibTeX
@article{yu2026toddlers,
title = {{Toddlers’ Active Gaze Behavior Supports Self‐Supervised Object Learning}},
author = {Zhengyang Yu and Arthur Aubret and Marcel C. Raabe and Jane Yang and Chen Yu and Jochen Triesch},
journal = {Developmental Science},
year = {2026},
month = jun,
doi = {10.1111/desc.70231},
url = {https://doi.org/10.1111/desc.70231},
note = {CC BY},
}
RIS
TY - JOUR
TI - Toddlers’ Active Gaze Behavior Supports Self‐Supervised Object Learning
AU - Zhengyang Yu
AU - Arthur Aubret
AU - Marcel C. Raabe
AU - Jane Yang
AU - Chen Yu
AU - Jochen Triesch
PY - 2026
DA - 2026/06/16
JO - Developmental Science
DO - 10.1111/desc.70231
UR - https://doi.org/10.1111/desc.70231
AB - Toddlers learn to recognize objects from different viewpoints with almost no supervision. During this learning, they execute frequent eye and head movements that shape their visual experience. It is presently unclear if and how these behaviors contribute to toddlers' emerging object recognition abilities. To answer this question, we here combine head-mounted eye tracking during dyadic play with unsupervised machine learning. We approximate toddlers' central visual field experience by cropping image regions from a head-mounted camera centered on the current gaze location estimated via eye tracking. This visual stream feeds a neural network model, which uses a biologically plausible unsupervised learning objective. Our experiments demonstrate that a few minutes of such first-person experience suffice to learn strong object representations permitting invariant object recognition. Importantly, by simulating alternative gaze behaviors we show that toddlers' eye movement patterns play a crucial role in this. Our analysis also reveals that the limited size of the central visual field where visual acuity is high plays an important role for successful learning. Together, this highlights the benefits of temporally structured visual experience arising from toddlers' natural interactions with objects. SUMMARY: We combine recordings of toddlers' first-person central visual field experience with biologically inspired self-supervised learning algorithms to model toddlers' development of invariant object recognition. Just a few minutes of toddlers' central visual field experience captured with head-mounted eye tracking suffice to learn strong object representations. Simulated alternative gaze behaviors produce weaker representations, demonstrating the importance of toddlers' active gaze strategies for learning. Our results emphasize the importance of toddlers' eye movements for learning object representations.
SN - 1363-755X
SN - 1467-7687
ER -