Anomaly Detection Requires Better Representations
It addresses the problem of detecting anomalies in unsupervised settings for science and industry, but is incremental as it builds on existing self-supervised methods.
The paper argues that while self-supervised representations have improved anomaly detection to state-of-the-art levels in benchmarks, future progress requires new advancements in representation learning.
Anomaly detection seeks to identify unusual phenomena, a central task in science and industry. The task is inherently unsupervised as anomalies are unexpected and unknown during training. Recent advances in self-supervised representation learning have directly driven improvements in anomaly detection. In this position paper, we first explain how self-supervised representations can be easily used to achieve state-of-the-art performance in commonly reported anomaly detection benchmarks. We then argue that tackling the next generation of anomaly detection tasks requires new technical and conceptual improvements in representation learning.