Reproducibility and Open Science are important to me. Consequently, my first-author publications have a corresponding github repository where I publish code, data, materials, models, and more.


Geirhos, R., Narayanappa, K., Mitzkus, B., Bethge, M., Wichmann, F. A., & Brendel, W. (2020). On the surprising similarities between supervised and self-supervised models. arXiv preprint arXiv:2010.08377. link

Borowski, J., Zimmermann, R. S., Schepers, J., Geirhos, R., Wallis, T. S. A., Bethge, M., & Brendel, W. (2020). Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations. arXiv preprint arXiv:2010.12606. link | code

Geirhos, R., Meding, K., & Wichmann, F. A. (2020). Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency. In Advances in Neural Information Processing Systems 33. link | code & data

Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020). Shortcut Learning in Deep Neural Networks. arXiv preprint arXiv:2004.07780. link | code

[ORAL] Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F. A., & Brendel, W. (2019). ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In International Conference on Learning Representations.
link | models, data & materials | training dataset

Michaelis, C., Mitzkus, B., Geirhos, R., Rusak, E., Bringmann, O., Ecker, A. S., Bethge, M., & Brendel, W. (2019). Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming. NeurIPS Workshop on Machine Learning for Autonomous Driving.
link | benchmark & data | imagecorruptions library

Haghiri, S., Rubisch, P., Geirhos, R., Wichmann, F., & von Luxburg, U. (2019). Comparison-based framework for psychophysics: Lab versus crowdsourcing. arXiv preprint arXiv:1905.07234.

Geirhos, R., Medina Temme, C. R., Rauber, J., Schütt, H. H., Bethge, M., & Wichmann, F. A. (2018). Generalisation in humans and deep neural networks. In Advances in Neural Information Processing Systems 31 (pp. 7548–7560).
link | data & materials

Geirhos, R., Janssen, D. H., Schütt, H. H., Rauber, J., Bethge, M., & Wichmann, F. A. (2017). Comparing deep neural networks against humans: object recognition when the signal gets weaker. arXiv preprint arXiv:1706.06969.
link | code, data & materials

Wichmann, F. A., Janssen, D. H., Geirhos, R., Aguilar, G., Schütt, H. H., Maertens, M., & Bethge, M. (2017). Methods and measurements to compare men against machines. Electronic Imaging, Human Vision and Electronic Imaging, 2017(14), 36–45.

Conference abstracts

Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020). Unintended cue learning: Lessons for deep learning from experimental psychology. Journal of Vision, 20(11), 652.

[ORAL] Geirhos, R., Rubisch, P., Rauber, J., Medina Temme, C. R., Michaelis, C., Brendel, W., Bethge, M., & Wichmann, F. A. (2019). Inducing a human-like shape bias leads to emergent human-level distortion robustness in CNNs. Journal of Vision, 19(10), 209c–209c.

Geirhos, R., Janssen, D., Schütt, H., Bethge, M., & Wichmann, F. (2017). Of human observers and deep neural networks: A detailed psychophysical comparison. Journal of Vision, 17(10), 806–806.

Butz, M. V., Geirhos, R., & Kneissler, J. (2015). An automatized Heider-Simmel story generation tool. In Proceedings of the 37th Annual Meeting of the Cognitive Science Society (CogSci), Pasadena, California, USA, July 22-25, 2015.
link | website & code