Toddlers' Active Gaze Behavior Supports Self-Supervised Object Learning
This work addresses a fundamental problem in developmental psychology and AI by explaining how toddlers learn objects with minimal supervision, though it is incremental in applying existing methods to new data.
The study tackled the problem of how toddlers' gaze behavior contributes to object recognition by combining head-mounted eye tracking with unsupervised learning, showing that their gaze strategy supports learning invariant object representations, with the limited central visual field being crucial.
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.