EUVIMEDEUVIMED entdecken
Crossref

UAD: A Unified Model for Zero-Shot Anomaly Detection

Yuqing Zhao, Min Meng, Jigang Wu, Ruiwei Xie

IEEE Transactions on Image Processing · 2026 · 35 · 8804-8818

DOI: 10.1109/tip.2026.3718433 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Yuqing Zhao und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangzhou Basic and Applied Basic Research Foundation, Guangdong Science and Technology Programme.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Zero-shot anomaly detection (ZSAD) aims to identify and localize anomalies in previously unseen target domains without accessing any target-domain training data, which is crucial under privacy, security, or proprietary constraints. However, existing ZSAD methods often struggle to generalize across domains, as they are tightly coupled to specific object categories or rely on fragmented designs that fail to capture both semantic consistency and structural abnormality. In this paper, we propose UAD, a unified framework that addresses ZSAD from a holistic perspective by jointly modeling semantic regularity and anomaly-aware representations. The key insight of UAD is that effective ZSAD requires aligning multi-level semantic understanding with fine-grained structural cues, rather than relying solely on object-centric semantics or local appearance statistics. To this end, UAD organizes image representations into coherent semantic contexts and identifies anomalies as deviations from both local structural patterns and high-level semantic consistency. Furthermore, we enhance cross-domain robustness by improving semantic supervision and diversity through prompt concatenation and intensity-guided anomaly synthesis, enabling UAD to better generalize to unseen anomaly types and domains. Extensive experiments on 17 real-world anomaly detection datasets show that UAD achieves superior zero-shot performance of detecting and segmenting anomalies in datasets of highly diverse class semantics from various defect inspection and medical imaging domains. Our works are available at https://github.com/hanli6688/UAD.

Förderung

  • National Natural Science Foundation of China
  • Guangzhou Basic and Applied Basic Research Foundation
  • Guangdong Science and Technology Programme

Zitieren

APA

Zhao, Y., Meng, M., Wu, J., & Xie, R. (2026). UAD: A Unified Model for Zero-Shot Anomaly Detection. IEEE Transactions on Image Processing, 35, 8804-8818. https://doi.org/10.1109/tip.2026.3718433

Vancouver

Zhao Y, Meng M, Wu J, Xie R. UAD: A Unified Model for Zero-Shot Anomaly Detection. IEEE Transactions on Image Processing. 2026;35:8804-8818. doi:10.1109/tip.2026.3718433

BibTeX
@article{Zhao2026,
  author = {Zhao, Yuqing and Meng, Min and Wu, Jigang and Xie, Ruiwei},
  title = {UAD: A Unified Model for Zero-Shot Anomaly Detection},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {8804--8818},
  doi = {10.1109/tip.2026.3718433}
}
Kostenlos starten →