FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization

TL;DR

FiLo introduces a zero-shot anomaly detection method that leverages fine-grained descriptions and high-quality localization techniques, significantly improving detection accuracy and localization precision across diverse object categories.

Contribution

The paper proposes FiLo, a novel ZSAD approach combining fine-grained anomaly descriptions with position-enhanced localization, addressing limitations of generic descriptions and single-patch similarity methods.

Findings

Achieves state-of-the-art AUC of 83.9% on VisA dataset.

Demonstrates improved localization accuracy with a pixel-level AUC of 95.9%.

Outperforms existing zero-shot anomaly detection methods.

Abstract

Zero-shot anomaly detection (ZSAD) methods entail detecting anomalies directly without access to any known normal or abnormal samples within the target item categories. Existing approaches typically rely on the robust generalization capabilities of multimodal pretrained models, computing similarities between manually crafted textual features representing "normal" or "abnormal" semantics and image features to detect anomalies and localize anomalous patches. However, the generic descriptions of "abnormal" often fail to precisely match diverse types of anomalies across different object categories. Additionally, computing feature similarities for single patches struggles to pinpoint specific locations of anomalies with various sizes and scales. To address these issues, we propose a novel ZSAD method called FiLo, comprising two components: adaptively learned Fine-Grained Description (FG-Des) and position-enhanced High-Quality Localization (HQ-Loc). FG-Des introduces fine-grained anomaly descriptions for each category using Large Language Models (LLMs) and employs adaptively learned textual templates to enhance the accuracy and interpretability of anomaly detection. HQ-Loc, utilizing Grounding DINO for preliminary localization, position-enhanced text prompts, and Multi-scale Multi-shape Cross-modal Interaction (MMCI) module, facilitates more accurate localization of anomalies of different sizes and shapes. Experimental results on datasets like MVTec and VisA demonstrate that FiLo significantly improves the performance of ZSAD in both detection and localization, achieving state-of-the-art performance with an image-level AUC of 83.9% and a pixel-level AUC of 95.9% on the VisA dataset. Code is available at https://github.com/CASIA-IVA-Lab/FiLo.