Metraipolis › archive › dc_ec45ce9119fe

VerdictAD: Few-Shot Anomaly Detection via Decision-Guided Refinement — arXiv:2611.02654

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02654
License (as archived)
CC0-1.0
Archived
2026-11-03T18:55:04.234Z
SHA-256 of the archived text
0b894f5e8ba67f6431fcf7e696fbab23c0071f1bdbae95bb1362793cca0ccd9c
Stable URL of this page
https://metraipolis.com/documento/dc_ec45ce9119fe

How to cite

VerdictAD: Few-Shot Anomaly Detection via Decision-Guided Refinement — arXiv:2611.02654 — arXiv (en), https://arxiv.org/abs/2611.02654 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec45ce9119fe (Metraipolis archive dc_ec45ce9119fe, sha256 0b894f5e8ba67f6431fcf7e696fbab23c0071f1bdbae95bb1362793cca0ccd9c)
BibTeX
@misc{dcec45ce9119fe,
  title = {VerdictAD: Few-Shot Anomaly Detection via Decision-Guided Refinement — arXiv:2611.02654},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02654},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec45ce9119fe; sha256 0b894f5e8ba67f6431fcf7e696fbab23c0071f1bdbae95bb1362793cca0ccd9c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02654. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Detecting defects in real-world industrial inspection often requires learning from only a few normal images per category. Recent few-shot anomaly detection methods have achieved strong performance by measuring feature differences between query images and normal references. However, visual differences do not always indicate genuine defects, as normal appearance variations can also produce high anomaly scores. Conversely, structural or logical anomalies may not produce strong local feature differences, making them difficult to detect. To address this limitation, we introduce VerdictAD, a training-free framework that refines existing anomaly detectors through visual decisions. Rather than replacing existing detectors, VerdictAD adopts a typed decision model to assess the query image and its local regions against a few normal references. By directly producing structured decision probabilities without text generation, the model provides complementary evidence for refining anomaly responses at different spatial scales. Building on this capability, we introduce two modules: Global Verdict Refinement (GVR) uses image-level decisions to refine the overall anomaly score, while Local Verdict Refinement (LVR) aggregates regional decisions to refine the anomaly map. Combined with a simple DINOv2-based detector, VerdictAD achieves competitive performance in one-shot and few-shot anomaly detection. More importantly, as a plug-and-play framework, it consistently improves existing anomaly detectors across MVTec AD, VisA, and MVTec LOCO AD, achieving strong results across one-shot and few-shot settings. Our code and experimental logs are publicly available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.02654 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:16:53.009Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).