# Toddlers' Active Gaze Behavior Supports Self-Supervised Object Learning

arXiv: https://arxiv.org/abs/2411.01969 · HTML: https://mlsanity.com/paper/2411.01969/

## 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 (most cited first, 20 of 20)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [MVImgNet: A Large-scale Dataset of Multi-view Images](https://mlsanity.com/paper/2303.06042/) (2023)
- [Self-supervised learning through the eyes of a child](https://mlsanity.com/paper/2007.16189/) (2020)
- [ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints](https://mlsanity.com/paper/2210.03895/) (2022)
- [Learning high-level visual representations from a child's perspective without strong inductive biases](https://mlsanity.com/paper/2305.15372/) (2023)
- [Self-supervised video pretraining yields robust and more human-aligned visual representations](https://mlsanity.com/paper/2210.06433/) (2022)
- [Towards Viewpoint-Invariant Visual Recognition via Adversarial Training](https://mlsanity.com/paper/2307.10235/) (2023)
- [Time to augment self-supervised visual representation learning](https://mlsanity.com/paper/2207.13492/) (2022)
- [Progress and limitations of deep networks to recognize objects in unusual poses](https://mlsanity.com/paper/2207.08034/) (2022)
- [On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation](https://mlsanity.com/paper/2112.07173/) (2021)
- [Self-supervised visual learning from interactions with objects](https://mlsanity.com/paper/2407.06704/) (2024)
- [Are Vision Transformers More Data Hungry Than Newborn Visual Systems?](https://mlsanity.com/paper/2312.02843/) (2023)
- [Self-supervised learning of video representations from a child's perspective](https://mlsanity.com/paper/2402.00300/) (2024)
- [Caregiver Talk Shapes Toddler Vision: A Computational Study of Dyadic Play](https://mlsanity.com/paper/2312.04118/) (2023)
- [Learning Object Semantic Similarity with Self-Supervision](https://mlsanity.com/paper/2405.05143/) (2024)
- [A Computational Account Of Self-Supervised Visual Learning From Egocentric Object Play](https://mlsanity.com/paper/2305.19445/) (2023)
- [Reverse-engineer the Distributional Structure of Infant Egocentric Views for Training Generalizable Image Classifiers](https://mlsanity.com/paper/2106.06694/) (2021)

## 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.