Deep Anomaly Detection Using Geometric Transformations

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

Introduction

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

Requirements

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

Citation

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

@inproceedings{NEURIPS2018_5e62d03a,
 author = {Golan, Izhak and El-Yaniv, Ran},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Deep Anomaly Detection Using Geometric Transformations},
 url = {https://proceedings.neurips.cc/paper/2018/file/5e62d03aec0d17facfc5355dd90d441c-Paper.pdf},
 volume = {31},
 year = {2018}
}