12 open source projects by bethgelab

Python package to corrupt arbitrary images.

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

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

Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

Siamese Mask R-CNN model for one-shot instance segmentation

Robustness and adaptation of ImageNet scale models. Pre-Release, stay tuned for updates.

Blind source separation based on the probabilistic tensor factorisation framework

NIPS Adversarial Vision Challenge

Convert Open Images annotations into MS Coco format to make it a drop in replacement

Adversarially Robust Neural Network on MNIST.

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

Information and scripts to run and develop the Bethge Lab Docker containers