To be presented in NIPS 2018 by Izhak Golan and Ran El-Yaniv.

This is the official implementation of "Deep Anomaly Detection Using Geometric Transformations". It includes all experiments reported in the paper.

• Python 3.5+
• Keras 2.2.0
• Tensorflow 1.8.0
• sklearn 0.19.1

If you use the ideas or method presented in the paper, please cite:

@article{golan2018deep,
  title={Deep Anomaly Detection Using Geometric Transformations},
  author={Golan, Izhak and El-Yaniv, Ran},
  journal={arXiv preprint arXiv:1805.10917},
  year={2018}
}