Foundation Models for Anomaly Detection: Vision and Challenges
This work addresses the problem of effective anomaly detection for various stakeholders across domains such as finance, manufacturing, and healthcare, providing an incremental step in leveraging foundation models for improved anomaly detection.
The authors tackled the problem of anomaly detection in various domains and presented a comprehensive review of foundation models' capabilities in enhancing anomaly identification, with unprecedented capabilities in data description and visual explanations. The survey proposes a novel taxonomy and outlines future research directions.
As data continues to grow in volume and complexity across domains such as finance, manufacturing, and healthcare, effective anomaly detection is essential for identifying irregular patterns that may signal critical issues. Recently, foundation models (FMs) have emerged as a powerful tool for advancing anomaly detection. They have demonstrated unprecedented capabilities in enhancing anomaly identification, generating detailed data descriptions, and providing visual explanations. This survey presents the first comprehensive review of recent advancements in FM-based anomaly detection. We propose a novel taxonomy that classifies FMs into three categories based on their roles in anomaly detection tasks, i.e., as encoders, detectors, or interpreters. We provide a systematic analysis of state-of-the-art methods and discuss key challenges in leveraging FMs for improved anomaly detection. We also outline future research directions in this rapidly evolving field.