Metraipolis › archive › dc_3dd4618eebcb
VariaFlow: Uncertainty-Aware Flow Matching for Unsupervised Anomaly Detection — arXiv:2610.41494
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41494
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:21:46.476Z
- SHA-256 of the archived text
d518e5efcbd38938bf3db7b9368a243854aa139d6d10046e2dc8e69248e874f6- Stable URL of this page
https://metraipolis.com/documento/dc_3dd4618eebcb
How to cite
VariaFlow: Uncertainty-Aware Flow Matching for Unsupervised Anomaly Detection — arXiv:2610.41494 — arXiv (en), https://arxiv.org/abs/2610.41494 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3dd4618eebcb (Metraipolis archive dc_3dd4618eebcb, sha256 d518e5efcbd38938bf3db7b9368a243854aa139d6d10046e2dc8e69248e874f6)
BibTeX
@misc{dc3dd4618eebcb,
title = {VariaFlow: Uncertainty-Aware Flow Matching for Unsupervised Anomaly Detection — arXiv:2610.41494},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41494},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3dd4618eebcb; sha256 d518e5efcbd38938bf3db7b9368a243854aa139d6d10046e2dc8e69248e874f6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41494. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reconstruction-based anomaly detection no longer fails at reconstruction. Generative models produce high-quality pseudo-healthy reconstructions, and the remaining difficulty is the step of scoring residuals. The residual between a scan and its reconstruction has two indistinguishable sources, genuine pathology and the anatomical variation that separates one healthy brain from another. Scoring against a single reconstruction treats both as anomalous, inflating false positives where healthy anatomy varies most while small or subtle lesions are lost in the surrounding reconstruction error. We identify the missing quantity as the predictive variance, how much a healthy reconstruction can vary at each location. We introduce VariaFlow, which estimates this variance from an ensemble of mask-guided restorations under an unconditional flow matching prior, each started from a different noise initialization, and which normalizes the residual by the resulting standard deviation. Few-step flow matching keeps the ensemble computationally affordable, and restoring at two spatial scales captures lesions of different size. Across three brain MRI datasets spanning stroke and tumor, VariaFlow is trained once on healthy anatomy and generalizes across all three, attaining the highest AUROC (0.94, 0.80, 0.78) on each and the highest AUPRC on both cross-domain datasets, exceeding the strongest baseline by 37% and 50%. Under domain shift, the same baseline drops by up to 52% in AUPRC, whereas VariaFlow stays more stable and achieves the best small-lesion Dice on all three datasets. 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/2610.41494 — 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 2026-11-03T08:06:38.833Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).