Bethge Lab

Pinned

1. foolbox Public

   A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

   Python 2.3k 403

2. model-vs-human Public

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

   Python 183 18

3. robust-detection-benchmark Public

   Code, data and benchmark from the paper "Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming" (NeurIPS 2019 ML4AD)

   Jupyter Notebook 153 23

4. imagecorruptions Public

   Python package to corrupt arbitrary images.

   Python 257 44

5. AnalysisBySynthesis Public

   Adversarially Robust Neural Network on MNIST.

   Python 59 18

6. stylize-datasets Public

   A script that applies the AdaIN style transfer method to arbitrary datasets

   Python 126 28