← Search

Samantha Marie Waters Wood

2 accepted papers

2024

A Newborn Embodied Turing Test for Comparing Object Segmentation Across Animals and Machines

ICLR 2024poster

Newborn brains rapidly learn to solve challenging object recognition tasks, including segmenting objects from backgrounds and recognizing objects across novel backgrounds and viewpoints. Conversely, modern machine-learning (ML) algorithms are "data hungry," requiring more training data than brains t…

Cited by 3SourcePDFScholar
2023

Are Vision Transformers More Data Hungry Than Newborn Visual Systems?

NeurIPS 2023poster

Vision transformers (ViTs) are top-performing models on many computer vision benchmarks and can accurately predict human behavior on object recognition tasks. However, researchers question the value of using ViTs as models of biological learning because ViTs are thought to be more “data hungry” than…