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. You can also find me on Google scholar.

Articles

[ORAL] Dehghani, M., Djolonga, J., Mustafa, B., Padlewski, P., Heek, J., Gilmer, J., Steiner, A., Caron, M., Geirhos, R., Alabdulmohsin, I. and Jenatton, R., …, Houlsby, N. (2023). Scaling vision transformers to 22 billion parameters. International Conference on Machine Learning.
link

Wichmann, F. A. & Geirhos, R. (2022). Are Deep Neural Networks Adequate Behavioral Models of Human Visual Perception? Annual Review of Vision Science, 9.
link

[AWARD] Geirhos, R. (2022). To err is human? A functional comparison of human and machine decision-making. Dissertation, University of Tübingen.
link

[AWARD] Sorscher, B., Geirhos, R., Shashank, S., Ganguli, S. & Morcos, A. S. (2022). Beyond neural scaling laws: beating power law scaling via data pruning. Advances in Neural Information Processing Systems 35.
link | code | data

Huber, L. S., Geirhos, R., & Wichmann, F. A. (2022). The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks. arXiv preprint arXiv:2205.10144.
link | code

Meding, K., Buschoff, L. M. S., Geirhos, R., & Wichmann, F. A. (2022). Trivial or impossible — dichotomous data difficulty masks model differences (on ImageNet and beyond). International Conference on Learning Representations.
link | code

[ORAL] Geirhos, R., Narayanappa, K., Mitzkus, B., Thieringer, T., Bethge, M., Wichmann, F. A., & Brendel, W. (2021). Partial success in closing the gap between human and machine vision. Advances in Neural Information Processing Systems 34.
link | code

[SPOTLIGHT] Zimmermann, R. S., Borowski, J., Geirhos, R., Bethge, M., Wallis, T. S. A., & Brendel, W. (2021). How Well do Feature Visualizations Support Causal Understanding of CNN Activations? Advances in Neural Information Processing Systems 34.
link | code | website

Huber, L. S., Geirhos, R., & Wichmann, F. A. (2021). Out-of-distribution robustness: Limited image exposure of a four-year-old is enough to outperform ResNet-50. NeurIPS workshop on Shared Visual Representations in Human & Machine Intelligence.
link

[ORAL] Geirhos, R., Narayanappa, K., Mitzkus, B., Bethge, M., Wichmann, F. A., & Brendel, W. (2020). On the surprising similarities between supervised and self-supervised models. NeurIPS workshop on Shared Visual Representations in Human & Machine Intelligence.
link

Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020). Shortcut Learning in Deep Neural Networks. Nature Machine Intelligence 2 (pp. 665–673).
link | code

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. International Conference on Learning Representations.
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. Advances in Neural Information Processing Systems 33.
link | code & data

[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. 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 | stylization code

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.
link

Geirhos, R., Medina Temme, C. R., Rauber, J., Schütt, H. H., Bethge, M., & Wichmann, F. A. (2018). Generalisation in humans and deep neural networks. 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.
link

Conference abstracts

[ORAL] Geirhos, R., Narayanappa, K., Mitzkus, B., Thieringer, T., Bethge, M., Wichmann, F. A., & Brendel, W. (2022). The bittersweet lesson: data-rich models narrow the behavioural gap to human vision. VSS 2022.
link

[ORAL] Huber, L. S., Geirhos, R., & Wichmann, F. A. (2021). The developmental trajectory of object recognition robustness: comparing children, adults, and CNNs. Journal of Vision, 21(9), 1967.
link

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.
link

[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.
link

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.
link

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