Multi-Normal Prototypes Learning for Weakly Supervised Anomaly Detection

TL;DR

This paper introduces a novel anomaly detection framework that models multiple normal subgroups and estimates the normality likelihood of unlabeled data, improving detection accuracy with limited labeled anomalies.

Contribution

It proposes multi-normal prototypes with deep clustering and contrastive learning, and a likelihood estimation method for unlabeled samples, addressing limitations of existing single-prototype and all-normal assumptions.

Findings

Outperforms state-of-the-art methods on various datasets.

Effectively models multiple normal subgroups.

Accurately estimates likelihood of unlabeled samples.

Abstract

Anomaly detection is a crucial task in various domains. Most of the existing methods assume the normal sample data clusters around a single central prototype while the real data may consist of multiple categories or subgroups. In addition, existing methods always assume all unlabeled samples are normal while some of them are inevitably being anomalies. To address these issues, we propose a novel anomaly detection framework that can efficiently work with limited labeled anomalies. Specifically, we assume the normal sample data may consist of multiple subgroups, and propose to learn multi-normal prototypes to represent them with deep embedding clustering and contrastive learning. Additionally, we propose a method to estimate the likelihood of each unlabeled sample being normal during model training, which can help to learn more efficient data encoder and normal prototypes for anomaly detection. Extensive experiments on various datasets demonstrate the superior performance of our method compared to state-of-the-art methods.