Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptation

About

Visual anomaly detection has been widely used in industrial inspection and medical diagnosis. Existing methods typically demand substantial training samples, limiting their utility in zero-/few-shot scenarios. While recent efforts have leveraged CLIP's zero-shot recognition capability for this task, they often ignore optimizing visual features to focus on local anomalies, reducing their efficacy. In this work, we propose AF-CLIP (Anomaly-Focused CLIP) by dramatically enhancing its visual representations to focus on local defects. Our approach introduces a lightweight adapter that emphasizes anomaly-relevant patterns in visual features, simultaneously optimizing both class-level features for image classification and patch-level features for precise localization. To capture anomalies of different sizes and improve detection accuracy, prior to the adapter, we develop a multi-scale spatial aggregation mechanism to effectively consolidate neighborhood context. Complementing these visual enhancements, we design learnable textual prompts that generically characterize normal and abnormal states. After optimization on auxiliary datasets using a composite objective function, AF-CLIP demonstrates strong zero-shot detection capability. Our method is also extended to few-shot scenarios by extra memory banks. Experimental results across diverse industrial and medical datasets demonstrate the effectiveness and generalization of our proposed method. Code is available at https://github.com/Faustinaqq/AF-CLIP.

Qingqing Fang, Wenxi Lv, Qinliang Su• 2025

Related benchmarks

TaskDatasetResultRank
Anomaly DetectionVisA
AUROC88.5
261
Anomaly DetectionMVTec
AUROC92.9
79
Anomaly LocalizationMVTec
AUC92.3
78
Anomaly DetectionHead-CT
AUROC0.912
71
Anomaly DetectionDTD
AUROC97.9
55
Anomaly DetectionBr35H
AUROC96.7
45
Anomaly LocalizationReal-IAD
P-AUROC95.5
43
Anomaly DetectionBTAD
AUROC94.3
41
Pixel-level Anomaly DetectionColonDB
AUROC83.2
39
Anomaly LocalizationBTAD
AUROC94.4
29
Showing 10 of 21 rows

Other info

Follow for update