English

Deep Anomaly Detection by Residual Adaptation

Machine Learning 2020-10-07 v1 Machine Learning

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T19:03:46.919Z