Pinned Loading

1. texture-vs-shape texture-vs-shape Public

   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)

   R 793 102

2. bethgelab/model-vs-human bethgelab/model-vs-human Public

   Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)

   Python 338 51

3. Stylized-ImageNet Stylized-ImageNet Public

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

   Python 508 64

4. academic-cv-publications academic-cv-publications Public

   Generate a customised list of publications for your LaTeX CV using BibTeX entries.

   TeX 97 16

5. google-research/fooling-feature-visualizations google-research/fooling-feature-visualizations Public

   Code for "Don't trust your eyes: on the (un)reliability of feature visualizations"

   Jupyter Notebook 31 3

6. bethgelab/imagecorruptions bethgelab/imagecorruptions Public

   Python package to corrupt arbitrary images.

   Python 416 67