English

Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics

Machine Learning 2023-02-14 v1

Abstract

One-class classification has been a prevailing method in building deep anomaly detection models under the assumption that a dataset consisting of normal samples is available. In practice, however, abnormal samples are often mixed in a training dataset, and they detrimentally affect the training of deep models, which limits their applicability. For robust normality learning of deep practical models, we propose an unsupervised deep one-class classification that learns normality from pseudo-labeled normal samples, i.e., outlier detection in single cluster scenarios. To this end, we propose a pseudo-labeling method by an adaptive threshold selected by ranking-based training dynamics. The experiments on 10 anomaly detection benchmarks show that our method effectively improves performance on anomaly detection by sizable margins.

Keywords

Cite

@article{arxiv.2302.06048,
  title  = {Unsupervised Deep One-Class Classification with Adaptive Threshold based on Training Dynamics},
  author = {Minkyung Kim and Junsik Kim and Jongmin Yu and Jun Kyun Choi},
  journal= {arXiv preprint arXiv:2302.06048},
  year   = {2023}
}

Comments

8 pages, 6 figures, 2022 IEEE International Conference on Data Mining Workshops (ICDMW)

R2 v1 2026-06-28T08:38:17.120Z