Active Gaze Behavior Boosts Self-Supervised Object Learning
Keywords: Gaze behavior, Self-supervised learning, Time-based augmentations, Object recognition
TL;DR: We reveal how infants’ gaze behavior supports self-supervised learning of view-invariant object recognition.
Abstract: Toddlers learn to recognize objects from different viewpoints with almost no supervision. Recent works argue that toddlers develop this ability by mapping close-in-time visual inputs to similar representations while interacting with objects. High acuity vision is only available in the central visual field, which may explain why toddlers (much like adults) constantly move around their gaze during such interactions. It is unclear whether/how much toddlers curate their visual experience through these eye movements to support their learning of object representations. In this work, we explore whether a bio-inspired visual learning model can harness toddlers’ gaze behavior during a play session to develop view-invariant object recognition. Exploiting head-mounted eye tracking during dyadic play, we simulate toddlers’ central visual field experience by cropping image regions centered on the gaze location. This visual stream feeds time-based self-supervised learning algorithms. Our experiments demonstrate that toddlers’ gaze strategy supports the learning of invariant object representations. Our analysis also reveals that the limited size of the central visual field where acuity is high is crucial for this. We further find that toddlers’ visual experience elicits more robust representations compared to adults’, mostly because toddlers look at objects they hold themselves for longer bouts. Overall, our work reveals how toddlers’ gaze behavior supports self-supervised learning of view-invariant object recognition.
Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 13831
Loading