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.
@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)