Journal
ELIFE
Volume 11, Issue -, Pages -Publisher
eLIFE SCIENCES PUBL LTD
DOI: 10.7554/eLife.74943
Keywords
infant development; categorization; object recognition; medial axis; one-shot learning; shape perception; Human
Categories
Funding
- National Institutes of Health [T32 HD071845]
Ask authors/readers for more resources
By comparing infants to computational models, this study sheds light on the origins and mechanisms underlying shape representations. The findings suggest that infants can form robust shape representations based on the skeletal structure when faced with variations in objects.
Categorization of everyday objects requires that humans form representations of shape that are tolerant to variations among exemplars. Yet, how such invariant shape representations develop remains poorly understood. By comparing human infants (6-12 months; N=82) to computational models of vision using comparable procedures, we shed light on the origins and mechanisms underlying object perception. Following habituation to a never-before-seen object, infants classified other novel objects across variations in their component parts. Comparisons to several computational models of vision, including models of high-level and low-level vision, revealed that infants' performance was best described by a model of shape based on the skeletal structure. Interestingly, infants outperformed a range of artificial neural network models, selected for their massive object experience and biological plausibility, under the same conditions. Altogether, these findings suggest that robust representations of shape can be formed with little language or object experience by relying on the perceptually invariant skeletal structure.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available