2.1k citations · 3.4k across the 13 of their papers we have counts for
4 papers · 1 filter
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
Robert Geirhos, Patricia Rubisch, Claudio Michaelis +3
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies suggest a more…
Generalisation in humans and deep neural networks
Robert Geirhos, Carlos R. Medina Temme, Jonas Rauber +3
We compare the robustness of humans and current convolutional deep neural networks (DNNs) on object recognition under twelve different types of image degradations. First, using thr…
Disentangling top-down vs. bottom-up and low-level vs. high-level influences on eye movements over time
Heiko H. Schütt, Lars O. M. Rothkegel, Hans A. Trukenbrod +2
Bottom-up and top-down, as well as low-level and high-level factors influence where we fixate when viewing natural scenes. However, the importance of each of these factors and how…
Searchers adjust their eye movement dynamics to the target characteristics in natural scenes
Lars Oliver Martin Rothkegel, Heiko Herbert Schütt, Hans Arne Trukenbrod +2
When searching a target in a natural scene, both the target's visual properties and similarity to the background influence whether (and how fast) humans are able to find it. Howeve…