Metraipolis › archive › dc_629cc273676f

Flownomaly: Single-Step Conditional-Mean Recovery for Few-Shot Anomaly Detection — arXiv:2610.32964

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32964
License (as archived)
CC0-1.0
Archived
2026-10-26T20:15:04.402Z
SHA-256 of the archived text
3573da909f0f36f91a206b09a31f1a1a8a0b8a0264d0aef8fca4ed48d1f954be
Stable URL of this page
https://metraipolis.com/documento/dc_629cc273676f

How to cite

Flownomaly: Single-Step Conditional-Mean Recovery for Few-Shot Anomaly Detection — arXiv:2610.32964 — arXiv (en), https://arxiv.org/abs/2610.32964 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_629cc273676f (Metraipolis archive dc_629cc273676f, sha256 3573da909f0f36f91a206b09a31f1a1a8a0b8a0264d0aef8fca4ed48d1f954be)
BibTeX
@misc{dc629cc273676f,
  title = {Flownomaly: Single-Step Conditional-Mean Recovery for Few-Shot Anomaly Detection — arXiv:2610.32964},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32964},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_629cc273676f; sha256 3573da909f0f36f91a206b09a31f1a1a8a0b8a0264d0aef8fca4ed48d1f954be},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32964. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Few-shot industrial anomaly detection requires modeling category-specific normality from only a handful of defect-free images. Common approaches tie inference to stored exemplars, impose rigid linear structure, or risk reproducing anomalous content. Flownomaly instead casts the problem as normal-counterpart recovery in frozen DINOv2 feature space. Given normal supports, a velocity field is learned through conditional flow matching over frozen patch tokens to transport Gaussian noise toward normal features. Along straight paths, a single recovery step using one evaluation of the optimal field yields the posterior mean of the clean normal token without trajectory integration. The operating time governs how strongly recovery modifies a query token. With no anomalous validation samples available for tuning, a normal-only Jacobian gain-to-noise criterion selects this time from the supports alone. Squared residuals between query tokens and their recovered counterparts yield anomaly signals for both dense localization and image-level detection. Across 1-, 2-, and 4-shot benchmarks on MVTec-AD and VisA, together with sample-shot evaluations on Real-IAD, Flownomaly achieves state-of-the-art performance against recent category-specific methods. In the 1-shot setting, image- and pixel-level AUROC reach 97.8% and 98.0% on MVTec-AD and 95.3% and 98.7% on VisA, with a 2.1-point image-level AUROC improvement over the strongest baseline on VisA. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.32964 — 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 2026-10-26T19:49:03.515Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).