Robert Geirhos

Shortcut learning in deep neural networks

Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis et al. · Nature Machine Intelligence · 2020 · 1.8K citations · Full text

Computing, Computer Engineering, Computer Science +8

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness

Robert Geirhos, Patricia Rubisch, Claudio Michaelis et al. · arXiv (Cornell University) · 2018 · 664 citations · Full text

Computing, Computer Science, Vision Science +17

Generalisation in humans and deep neural networks

Robert Geirhos, Carlos R. Medina Temme, Jonas Rauber et al. · Max Planck Digital Library · 2018 · 289 citations · Full text

Computing, Computer Science, Vision Science +16

Generalisation in humans and deep neural networks

Robert Geirhos, Carlos R. Medina Temme, Jonas Rauber et al. · arXiv (Cornell University) · 2018 · 240 citations · Full text

Computing, Computer Science, Vision Science +16

Benchmarking Robustness in Object Detection: Autonomous Driving when\n Winter is Coming

Claudio Michaelis, Benjamin Mitzkus, Robert Geirhos et al. · arXiv (Cornell University) · 2019 · 199 citations · Full text

Computing, Autonomous Systems, Computer Science +16