no code implementations • 28 Nov 2022 • Tal Golan, Wenxuan Guo, Heiko H. Schütt, Nikolaus Kriegeskorte
Comparing representations of complex stimuli in neural network layers to human brain representations or behavioral judgments can guide model development.
no code implementations • 27 May 2022 • Heiko H. Schütt, Wei Ji Ma
A visual system has to learn both which features to extract from images and how to group locations into (proto-)objects.
no code implementations • 16 Dec 2021 • Heiko H. Schütt, Alexander D. Kipnis, Jörn Diedrichsen, Nikolaus Kriegeskorte
However, we lack robust methods for connecting theory and experiment by evaluating our new big models with our new big data.
1 code implementation • 28 Dec 2020 • Alban Flachot, Arash Akbarinia, Heiko H. Schütt, Roland W. Fleming, Felix A. Wichmann, Karl R. Gegenfurtner
High levels of color constancy were achieved with different DNN architectures.
2 code implementations • NeurIPS 2018 • Robert Geirhos, Carlos R. Medina Temme, Jonas Rauber, Heiko H. Schütt, Matthias Bethge, Felix A. Wichmann
We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object recognition under twelve different types of image degradations.
1 code implementation • 21 Jun 2017 • Robert Geirhos, David H. J. Janssen, Heiko H. Schütt, Jonas Rauber, Matthias Bethge, Felix A. Wichmann
In addition, we find progressively diverging classification error-patterns between humans and DNNs when the signal gets weaker, indicating that there may still be marked differences in the way humans and current DNNs perform visual object recognition.