ROADS: Robust Prompt-driven Multi-Class Anomaly Detection under Domain Shift

TL;DR

ROADS introduces a prompt-driven multi-class anomaly detection framework that effectively handles domain shifts and class interference, improving robustness and accuracy in real-world scenarios.

Contribution

The paper presents ROADS, a novel MUAD framework with hierarchical prompts and domain adaptation, addressing class interference and domain shift issues.

Findings

Outperforms state-of-the-art in anomaly detection and localization

Demonstrates robustness against domain shifts

Effective in out-of-distribution settings

Abstract

Recent advancements in anomaly detection have shifted focus towards Multi-class Unified Anomaly Detection (MUAD), offering more scalable and practical alternatives compared to traditional one-class-one-model approaches. However, existing MUAD methods often suffer from inter-class interference and are highly susceptible to domain shifts, leading to substantial performance degradation in real-world applications. In this paper, we propose a novel robust prompt-driven MUAD framework, called ROADS, to address these challenges. ROADS employs a hierarchical class-aware prompt integration mechanism that dynamically encodes class-specific information into our anomaly detector to mitigate interference among anomaly classes. Additionally, ROADS incorporates a domain adapter to enhance robustness against domain shifts by learning domain-invariant representations. Extensive experiments on MVTec-AD and VISA datasets demonstrate that ROADS surpasses state-of-the-art methods in both anomaly detection and localization, with notable improvements in out-of-distribution settings.