Metraipolis › archive › dc_7cdc1aaf8cbc
SPARC: Subspace Position-Aware Robust Few-Shot Calibration for Distribution-Shifted Industrial Anomaly Detection — arXiv:2608.18585
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.18585
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:06:17.565Z
- SHA-256 of the archived text
a1ac77cd94801aab0a46828ed1258214918bf593c32d87c41fb7d8ab3f544e29- Stable URL of this page
https://metraipolis.com/documento/dc_7cdc1aaf8cbc
How to cite
SPARC: Subspace Position-Aware Robust Few-Shot Calibration for Distribution-Shifted Industrial Anomaly Detection — arXiv:2608.18585 — arXiv (en), https://arxiv.org/abs/2608.18585 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cdc1aaf8cbc (Metraipolis archive dc_7cdc1aaf8cbc, sha256 a1ac77cd94801aab0a46828ed1258214918bf593c32d87c41fb7d8ab3f544e29)
BibTeX
@misc{dc7cdc1aaf8cbc,
title = {SPARC: Subspace Position-Aware Robust Few-Shot Calibration for Distribution-Shifted Industrial Anomaly Detection — arXiv:2608.18585},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.18585},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cdc1aaf8cbc; sha256 a1ac77cd94801aab0a46828ed1258214918bf593c32d87c41fb7d8ab3f544e29},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18585. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-based industrial anomaly detectors are calibrated on one distribution but may be deployed on another that differs in illumination, fixture placement, or sensor characteristics, sharply degrading an otherwise accurate detector. Adapting to the incoming lot is a natural response, but labeled anomalies are scarce. We therefore consider calibration using only a handful of verified-normal images available before scoring the rest of the lot. Existing fixes require backpropagation, detector-specific tuning, or choices about feature directions that few calibration samples cannot justify. We present SPARC, a few-shot calibration method that intercepts patch features between encoder and detector and removes a closed-form, spatially indexed estimate of deployment-time nuisance through per-cell subspace projection. It needs only $k \le 8$ verified-normal images and uses the algebraic saturation rank $r{=}k{-}1$ on the encoder's native patch grid. The correction requires no gradient or weight updates and works with memory-bank, density, prototype, and mutual detectors. On the shift-prone benchmarks, SPARC improves pooled Image AUROC and AU-PRO$_{0.3}$ for all seven detectors whose image scores depend on corrected patch features by $+13.8$ and $+3.5$ percentage points (pp), respectively; on benchmarks without engineered shift, the changes are small and mixed. Controls that give competing corrections the same calibration images attribute these gains to the per-cell subspace structure rather than the images alone. Further ablations support the saturation-rank choice and characterize sensitivity to backbone and calibration conditions.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.18585 — 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 2026-10-18T14:00:22.555Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).