Anomaly-Aware Vision-Language Adapters for Zero-Shot Anomaly Detection

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Aqeel, Muhammad, Nazir, Maham, Khan, Uzair, Cristani, Marco, Setti, Francesco
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909036110151680
author Aqeel, Muhammad
Nazir, Maham
Khan, Uzair
Cristani, Marco
Setti, Francesco
author_facet Aqeel, Muhammad
Nazir, Maham
Khan, Uzair
Cristani, Marco
Setti, Francesco
contents Zero-shot anomaly detection aims to identify defects in unseen categories without target-specific training. Existing methods usually apply the same feature transformation to all samples, treating normal and anomalous data uniformly despite their fundamentally asymmetric distributions, compact normals versus diverse anomalies. We instead exploit this natural asymmetry by proposing AVA-DINO, an anomaly-aware vision-language adaptation framework with dual specialized branches for normal and anomalous patterns that adapt frozen DINOv3 visual features. During training on auxiliary data, the two branches are learned jointly with a text-guided routing mechanism and explicit routing regularization that encourages branch specialization. At test time, only the input image and fixed, predefined language descriptions are used to dynamically combine the two branches, enabling an asymmetric activation. This design prevents degenerate uniform routing and allows context-specific feature transformations. Experiments across nine industrial and medical benchmarks demonstrate state-of-the-art performance, achieving 93.5% image-AUROC on MVTec-AD and strong cross-domain generalization to medical imaging without domain-specific fine-tuning. https://github.com/aqeeelmirza/AVA-DINO
format Preprint
id arxiv_https___arxiv_org_abs_2605_12069
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Anomaly-Aware Vision-Language Adapters for Zero-Shot Anomaly Detection
Aqeel, Muhammad
Nazir, Maham
Khan, Uzair
Cristani, Marco
Setti, Francesco
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Zero-shot anomaly detection aims to identify defects in unseen categories without target-specific training. Existing methods usually apply the same feature transformation to all samples, treating normal and anomalous data uniformly despite their fundamentally asymmetric distributions, compact normals versus diverse anomalies. We instead exploit this natural asymmetry by proposing AVA-DINO, an anomaly-aware vision-language adaptation framework with dual specialized branches for normal and anomalous patterns that adapt frozen DINOv3 visual features. During training on auxiliary data, the two branches are learned jointly with a text-guided routing mechanism and explicit routing regularization that encourages branch specialization. At test time, only the input image and fixed, predefined language descriptions are used to dynamically combine the two branches, enabling an asymmetric activation. This design prevents degenerate uniform routing and allows context-specific feature transformations. Experiments across nine industrial and medical benchmarks demonstrate state-of-the-art performance, achieving 93.5% image-AUROC on MVTec-AD and strong cross-domain generalization to medical imaging without domain-specific fine-tuning. https://github.com/aqeeelmirza/AVA-DINO
title Anomaly-Aware Vision-Language Adapters for Zero-Shot Anomaly Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2605.12069