Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection

TL;DR

This paper introduces ALFA, a training-free method that enhances zero-shot visual anomaly detection using large vision-language models by adaptively generating prompts and aligning local image semantics for improved localization accuracy.

Contribution

ALFA employs a run-time prompt adaptation and a novel local semantic aligner to improve zero-shot anomaly detection and localization in vision-language models.

Findings

Achieves 12.1% PRO improvement on MVTec dataset.

Achieves 8.9% PRO improvement on VisA dataset.

Effective in leveraging language models for precise anomaly localization.

Abstract

Large vision-language models (LVLMs) are markedly proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) challenges by pairing images with textual descriptions indicative of normal and abnormal conditions, referred to as anomaly prompts. However, existing approaches depend on static anomaly prompts that are prone to cross-semantic ambiguity, and prioritize global image-level representations over crucial local pixel-level image-to-text alignment that is necessary for accurate anomaly localization. In this paper, we present ALFA, a training-free approach designed to address these challenges via a unified model. We propose a run-time prompt adaptation strategy, which first generates informative anomaly prompts to leverage the capabilities of a large language model (LLM). This strategy is enhanced by a contextual scoring mechanism for per-image anomaly prompt adaptation and cross-semantic ambiguity mitigation. We further introduce a novel fine-grained aligner to fuse local pixel-level semantics for precise anomaly localization, by projecting the image-text alignment from global to local semantic spaces. Extensive evaluations on MVTec and VisA datasets confirm ALFA's effectiveness in harnessing the language potential for zero-shot VAD, achieving significant PRO improvements of 12.1% on MVTec and 8.9% on VisA compared to state-of-the-art approaches.