Deep anomaly detection is a difficult task since, in high dimensions, it is hard to completely characterize a notion of "differentness" when given only examples of normality. In this paper we propose a novel approach to deep anomaly detection based on augmenting large pretrained networks with residual corrections that adjusts them to the task of anomaly detection. Our method gives rise to a highly parameter-efficient learning mechanism, enhances disentanglement of representations in the pretrained model, and outperforms all existing anomaly detection methods including other baselines utilizing pretrained networks. On the CIFAR-10 one-versus-rest benchmark, for example, our technique raises the state of the art from 96.1 to 99.0 mean AUC.
@article{arxiv.2010.02310,
title = {Deep Anomaly Detection by Residual Adaptation},
author = {Lucas Deecke and Lukas Ruff and Robert A. Vandermeulen and Hakan Bilen},
journal= {arXiv preprint arXiv:2010.02310},
year = {2020}
}