Skip to content

Official code repository for paper Zero-Shot Anomaly Detection via Batch Normalization (NeurIPS 2023).

License

Notifications You must be signed in to change notification settings

aodongli/zero-shot-ad-via-batch-norm

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Zero-Shot Anomaly Detection via Batch Normalization

Official code repository for NeurIPS 2023 paper Zero-Shot Anomaly Detection via Batch Normalization.

Code for different datasets is shown in the folder names. Refer to each folder for the datasets of interest.

Package requirements are listed in each folder's requirements.txt. Run pip install -r requireme.txt to install all packages.

Brief Overview

We introduce a straightforward yet powerful approach to train an out-of-box deep anomaly detector into a zero-shot anomaly detector. This method requires minimal configurations: 1) ensure that the deep model is set for batch-level prediction and 2) maintain all batch normalization layers in the training mode during inference. Below, you'll find a step-by-step comparison with the traditional stationary anomaly detection framework. Key configurations are color-highlighted for clarity. More details can be found in the full paper.

acr


@inproceedings{acr,
  title={Zero-Shot Anomaly Detection via Batch Normalization},
  author={Li, Aodong and Qiu, Chen and Kloft, Marius and Smyth, Padhraic and Rudolph, Maja and Mandt, Stephan},
  booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
  year={2023}
}

About

Official code repository for paper Zero-Shot Anomaly Detection via Batch Normalization (NeurIPS 2023).

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages