Foundation Models and Transformers for Anomaly Detection: A Survey

TL;DR

This survey reviews how Transformers and foundation models revolutionize visual anomaly detection by improving robustness, interpretability, and scalability through attention mechanisms and large-scale pre-training.

Contribution

It categorizes VAD methods and highlights the paradigm shift enabled by foundation models and Transformers in the field.

Findings

Transformers enhance long-range dependency modeling in VAD.

Foundation models improve robustness and scalability of anomaly detection.

Attention mechanisms enable more interpretable VAD solutions.

Abstract

In line with the development of deep learning, this survey examines the transformative role of Transformers and foundation models in advancing visual anomaly detection (VAD). We explore how these architectures, with their global receptive fields and adaptability, address challenges such as long-range dependency modeling, contextual modeling and data scarcity. The survey categorizes VAD methods into reconstruction-based, feature-based and zero/few-shot approaches, highlighting the paradigm shift brought about by foundation models. By integrating attention mechanisms and leveraging large-scale pre-training, Transformers and foundation models enable more robust, interpretable, and scalable anomaly detection solutions. This work provides a comprehensive review of state-of-the-art techniques, their strengths, limitations, and emerging trends in leveraging these architectures for VAD.