Dr Yaniv Morgenstern | Towards understanding human shape representation with image-computable models
Guest Lecture
- Date: Jun 14, 2021
- Time: 04:00 PM - 05:00 PM (Local Time Germany)
- Speaker: Dr Yaniv Morgenstern
- Psychology and Sports Science, Department of Psychology, Justus Liebig University Giessen, Germany
- Location: MPI for Human Cognitive and Brain Sciences
- Room: Zoom Meeting
- Host: CBS CoCoNUT
An objects shape helps us recover what it is and how it works, even if we
have never seen it before. A major debate in cognitive science and AI
research is whether our brains achieve such abilities using dumb but
efficient heuristics or deep but costly rational computations, or both.
In this talk, I will present my recent work constructing ShapeCompa
psychophysically-validated, heuristics-based model of human shape
similarity a tool that will help us understand computations underlying
human shape perception. Merging computer vision models and Generative
Adversarial Networks from machine learning, I show how ShapeComp is highly
predictive of human shape similarity across novel shape pairs and larger
shape sets. I describe how ShapeComp can be used to synthesize carefully
controlled datasets that allow experimenters to decouple heuristic and
rational explanations, and test when deeper, more causal variables underlie
our perception of shape and its characteristics.