Metraipolis › archive › dc_a49464aaef67
Training-Free Logical and Structural Anomaly Detection via Calibrated Fusion — arXiv:2609.05091
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05091
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T23:41:20.877Z
- SHA-256 of the archived text
3e1381c7bb95fa1b70ebd536e7711f7323eac344df0ad39f204be7827ff27674- Stable URL of this page
https://metraipolis.com/documento/dc_a49464aaef67
How to cite
Training-Free Logical and Structural Anomaly Detection via Calibrated Fusion — arXiv:2609.05091 — arXiv (en), https://arxiv.org/abs/2609.05091 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a49464aaef67 (Metraipolis archive dc_a49464aaef67, sha256 3e1381c7bb95fa1b70ebd536e7711f7323eac344df0ad39f204be7827ff27674)
BibTeX
@misc{dca49464aaef67,
title = {Training-Free Logical and Structural Anomaly Detection via Calibrated Fusion — arXiv:2609.05091},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05091},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a49464aaef67; sha256 3e1381c7bb95fa1b70ebd536e7711f7323eac344df0ad39f204be7827ff27674},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05091. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Industrial anomaly detection must handle two distinct defect families: structural anomalies, which manifest as local texture corruptions, and logical anomalies, which violate global rules on object count, composition, or arrangement. Existing detectors typically favor one family at the expense of the other. In particular, training-free methods effectively exploit frozen representations but lack an explicit notion of object count, while methods that reason about counts usually rely on category-specific component modeling. We show that counting ability can be introduced into training-free anomaly detection without additional training or part-level supervision. Our key idea is a normal-set calibration that aligns heterogeneous anomaly cues using statistics from normal images, enabling their direct fusion within a unified training-free framework. Built upon this calibration, our detector combines complementary frozen cues to address both logical and structural anomalies. On MVTec-LOCO, our method achieves image-level AUROCs of 89.0 and 95.9 on logical and structural anomalies, respectively, yielding a 92.5 average---the best among training-free detectors in our comparison. It remains competitive with methods requiring network training or part annotations, while its structural variant matches PatchCore on MVTec-AD (99.1 image-AUROC), suggesting that the proposed calibration generalizes beyond logical anomaly detection. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.05091 — 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 2026-10-16T23:16:11.439Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).