The Perception of Object Shape in Humans and Machines
Abstract
This talk focuses on how humans process and understand shape information. I will present ShapeComp, a novel computational model that predicts human shape similarity judgments with high accuracy. The model, based on the statistics of natural animal shapes, outperforms traditional object recognition neural networks in capturing human-like shape representations. The lecture demonstrates the utility of ShapeComp in three key areas:
- Automatic generation of perceptually uniform shape spaces for experimental stimuli
- Investigation of high-level shape aftereffects in human vision
- Potential improvements to the robustness of object recognition neural networks
The overarching goal of this work is to better understand human visual reasoning capabilities, particularly in situations with limited data, and to develop more human-like artificial intelligence systems. This research has implications for cognitive science, computer vision, and the development of more robust and generalizable AI models that can process visual information in ways more closely aligned with human perception.
About Yaniv
Dr. Yaniv Morgenstern is a cognitive scientist specializing in visual perception and computational modeling of human cognition. After completing his doctoral studies at York University in Canada, Yaniv embarked on a diverse postdoctoral journey. His research took him across the globe, with positions in Singapore, USA, Germany, and Belgium. Currently, Dr. Morgenstern serves as an Assistant Professor in the Psychology Department at Erasmus University Rotterdam. In this role, he continues to bridge the gap between human perception and machine learning, with the goal of developing more human-like artificial intelligence systems. His interdisciplinary approach combines methods from psychology, neuroscience, and computer science to advance our understanding of visual cognition.
