#Human-vision

rgeirhos

texture-vs-shape

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

rgeirhos

Stylized-ImageNet

Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)

rgeirhos

generalisation-humans-DNNs

Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)