English

Masked Contrastive Learning for Anomaly Detection

Machine Learning 2023-01-31 v2 Computer Vision and Pattern Recognition

Abstract

Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their efficiencies. In particular, self-supervised learning based methods are spurring interest due to their capability of learning diverse representations without additional labels. Among self-supervised learning tactics, contrastive learning is one specific framework validating their superiority in various fields, including anomaly detection. However, the primary objective of contrastive learning is to learn task-agnostic features without any labels, which is not entirely suited to discern anomalies. In this paper, we propose a task-specific variant of contrastive learning named masked contrastive learning, which is more befitted for anomaly detection. Moreover, we propose a new inference method dubbed self-ensemble inference that further boosts performance by leveraging the ability learned through auxiliary self-supervision tasks. By combining our models, we can outperform previous state-of-the-art methods by a significant margin on various benchmark datasets.

Keywords

Cite

@article{arxiv.2105.08793,
  title  = {Masked Contrastive Learning for Anomaly Detection},
  author = {Hyunsoo Cho and Jinseok Seol and Sang-goo Lee},
  journal= {arXiv preprint arXiv:2105.08793},
  year   = {2023}
}

Comments

Accepted to IJCAI 2021

R2 v1 2026-06-24T02:14:26.746Z