mlsanityData to 14 Oct 2026

Toddlers' Active Gaze Behavior Supports Self-Supervised Object Learning

arXiv 2411.01969 ↗First posted 4 Nov 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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 an unsupervised computational model of toddlers' learning, which constructs visual representations that slowly change over time. Our experiments demonstrate that toddlers' gaze strategy supports the learning of invariant object representations. Our analysis also shows that the limited size of the central visual field where acuity is high is crucial for this. Overall, our work reveals how toddlers' gaze behavior may support their development of view-invariant object recognition.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 57 references that are in the map. First posted on arXiv 4 Nov 2024.

Builds on

20 of 57 references.

References · 20

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  3. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  4. 2022VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Trainingcited by 395
  5. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 220
  6. 2020Self-supervised learning through the eyes of a childcited by 61
  7. 2022ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpointscited by 48
  8. 2023Learning high-level visual representations from a child's perspective without strong inductive biasescited by 22
  9. 2022Self-supervised video pretraining yields robust and more human-aligned visual representationscited by 20
  10. 2023Towards Viewpoint-Invariant Visual Recognition via Adversarial Trainingcited by 19
  11. 2022Time to augment self-supervised visual representation learningcited by 15
  12. 2022Progress and limitations of deep networks to recognize objects in unusual posescited by 13
8 more
  1. 2021On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentationcited by 12
  2. 2024Self-supervised visual learning from interactions with objectscited by 10
  3. 2023Are Vision Transformers More Data Hungry Than Newborn Visual Systems?cited by 7
  4. 2024Self-supervised learning of video representations from a child's perspectivecited by 6
  5. 2023Caregiver Talk Shapes Toddler Vision: A Computational Study of Dyadic Playcited by 5
  6. 2024Learning Object Semantic Similarity with Self-Supervisioncited by 5
  7. 2023A Computational Account Of Self-Supervised Visual Learning From Egocentric Object Playcited by 4
  8. 2021Reverse-engineer the Distributional Structure of Infant Egocentric Views for Training Generalizable Image Classifierscited by 1

Built on by

Not cited yet.