Search

Robert Geirhos

Don't trust your eyes: on the (un) reliability of feature visualizations
The bittersweet lesson: data-rich models narrow the behavioural gap to human vision
How Well do Feature Visualizations Support Causal Understanding of CNN Activations?
Partial success in closing the gap between human and machine vision
Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations
Unintended cue learning: Lessons for deep learning from experimental psychology
On the surprising similarities between supervised and self-supervised models
Shortcut Learning in Deep Neural Networks
Inducing a human-like shape bias leads to emergent human-level distortion robustness in CNNs
Benchmarking robustness in object detection: Autonomous driving when winter is coming
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness

Published with Wowchemy — the free, open source website builder that empowers creators.