Elsa: Energy-based learning for semi-supervised anomaly detection. (arXiv:2103.15296v2 [cs.CV] UPDATED)

Anomaly detection aims at identifying deviant instances from the normal data
distribution. Many advances have been made in the field, including the
innovative use of unsupervised contrastive learning. However, existing methods
generally assume clean training data and are limited when the data contain
unknown anomalies. This paper presents Elsa, a novel semi-supervised anomaly
detection approach that unifies the concept of energy-based models with
unsupervised contrastive learning. Elsa instills robustness against any data
contamination by a carefully designed fine-tuning step based …

anomaly detection arxiv cv detection energy learning