In this repository, you find the code to run the experiments of all three case studies and the corresponding visualizations published in
Five Points to Check when Comparing Visual Perception in Humans and Machines
Christina M. Funke*, Judy Borowski*, Karolina Stosio, Wieland Brendel+, Thomas S. A. Wallis+, Matthias Bethge+
Previous title of the manuscript: "The Notorious Difficulty of Comparing Human and Machine Perception"
The code is organized according to the three case studies:
- Closed Contour Detection
- Synthetic Visual Reasoning Test
- Recognition Gap
If you find this code useful for your scientific work, please consider citing it in resulting publications:
@article{funke2021five,
title={Five points to check when comparing visual perception in humans and machines},
author={Funke, Christina M and Borowski, Judy and Stosio, Karolina and Brendel, Wieland and Wallis, Thomas SA and Bethge, Matthias},
journal={Journal of Vision},
volume={21},
number={3},
pages={16--16},
year={2021},
publisher={The Association for Research in Vision and Ophthalmology}
}
- Christina Funke
- Judy Borowski