Metraipolis › archive › dc_f4233105d3da
NFAD: Nuisance-Filtered Anomaly Detection Under Distribution Shift — arXiv:2608.29112
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29112
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:53:32.604Z
- SHA-256 of the archived text
8ff1a51f71f0fc5ae2a8689cecad4b5411d59aa070d60b09b12f139e76c279a0- Stable URL of this page
https://metraipolis.com/documento/dc_f4233105d3da
How to cite
NFAD: Nuisance-Filtered Anomaly Detection Under Distribution Shift — arXiv:2608.29112 — arXiv (en), https://arxiv.org/abs/2608.29112 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f4233105d3da (Metraipolis archive dc_f4233105d3da, sha256 8ff1a51f71f0fc5ae2a8689cecad4b5411d59aa070d60b09b12f139e76c279a0)
BibTeX
@misc{dcf4233105d3da,
title = {NFAD: Nuisance-Filtered Anomaly Detection Under Distribution Shift — arXiv:2608.29112},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29112},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f4233105d3da; sha256 8ff1a51f71f0fc5ae2a8689cecad4b5411d59aa070d60b09b12f139e76c279a0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29112. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent advances in anomaly detection (AD) for industrial inspection have pushed performance on standard benchmarks toward saturation. However, strong benchmark performance does not necessarily translate to real-world deployment, as these benchmarks are primarily collected under controlled acquisition conditions. Changes in illumination, background, viewpoint, and other environmental factors can shift normal samples away from the learned normal distribution and cause false anomaly responses. We address AD under such distribution shifts by explicitly modeling nuisance variation from changing imaging conditions in feature space. Without anomaly labels or target-domain data, our Nuisance-Filtered Anomaly Detection (NFAD) framework estimates a nuisance subspace from matched feature displacements induced by content-preserving perturbations and suppresses its contribution to anomaly residuals at inference. The same subspace supports two complementary branches: full projection for image-level detection and selective suppression for pixel-level localization, preserving evidence of localized defects. On AeBAD-S, a benchmark specifically designed for AD under acquisition shifts, NFAD achieves 91.0\% image-level AUROC, establishing a new state of the art. Notably, this robustness does not come at the expense of conventional AD performance: NFAD remains competitive on standard benchmarks that do not explicitly evaluate distribution shift, including VisA, Real-IAD, and MVTec AD. These results show that explicitly suppressing such nuisance variation improves AD under distribution shift while preserving strong performance in standard settings. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.29112 — 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 2026-10-17T09:28:47.980Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).