Keynotes | K&Ts | GACs | Talks | Posters | Search

Poster A in Poster Session A: Tuesday, August 4, 9:30 – 11:15 am, Kimmel Center, Shorin & Rosenthal Rooms

The role of shape and local features in human object recognition and learning

Allan R. Schneider¹, Olivia Maltz¹, Vladislav Ayzenberg¹; ¹Temple University

Presenter: Allan R. Schneider

An object’s shape is an important visual cue, critical for both perception and cognition. However, the current best models of human vision, Deep Neural Networks (DNNs), do not use shape, but instead they rely on local visual features. This raises the question, is shape less important for human perception than previously believed? In six experiments, with adults, children, and DNNs, we tested the role of shape and local features in object recognition and learning. We found that local visual features were sufficient for recognizing familiar objects, but that shape was crucial for one-shot object learning. Together, these findings force us to reevaluate the role of shape in visual recognition and suggest that DNNs, despite not using shape, may nevertheless capture an important aspect of human visual processing.

Topic Area: Computational Models of Vision & Visual Cortex