Metraipolis › archive › dc_71cfa74aedba

LUMIN: Lightweight Universal Manufacturing Inspection Network for Anomaly Detection — arXiv:2609.04775

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.04775
License (as archived): CC0-1.0
Archived: 2026-10-16T23:33:29.078Z
SHA-256 of the archived text: 416fa67d6707bea53dbb2f5bac3b7d61f6d6f8a48703d969b04a3539a610bf2d
Stable URL of this page: https://metraipolis.com/documento/dc_71cfa74aedba

How to cite

LUMIN: Lightweight Universal Manufacturing Inspection Network for Anomaly Detection — arXiv:2609.04775 — arXiv (en), https://arxiv.org/abs/2609.04775 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_71cfa74aedba (Metraipolis archive dc_71cfa74aedba, sha256 416fa67d6707bea53dbb2f5bac3b7d61f6d6f8a48703d969b04a3539a610bf2d)

BibTeX

@misc{dc71cfa74aedba,
  title = {LUMIN: Lightweight Universal Manufacturing Inspection Network for Anomaly Detection — arXiv:2609.04775},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04775},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_71cfa74aedba; sha256 416fa67d6707bea53dbb2f5bac3b7d61f6d6f8a48703d969b04a3539a610bf2d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04775. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial anomaly detection faces two engineering bottlenecks: memory bank construction latency and inference efficiency. Traditional sampling algorithms (Farthest Point Sampling, K-Means, etc.) rely on numerous backbone forward passes and iterative distance computations, with construction times ranging from minutes to hours; heavy computation components such as multi-scale feature extraction struggle to meet the millisecond-level real-time requirements of production lines. This paper focuses on sampling efficiency and inference optimization for industrial deployment with two core contributions: (1) PSP (Plugin Sampler Pipeline)---a four-stage adaptive memory bank sampling pipeline based on 18-dimensional pixel metadata and five complementary visual plugins. PSP completes all sampling with zero backbone forward passes; coarse filtering is sub-second numerical sorting, and metadata extraction is a one-time offline cost. PSP supports progressive deployment and incremental updates. (2) Two engineering optimization strategies---parallel memory bank similarity computation (reducing inference memory and latency by over 95\%) and stratified pixel sampling for large-scale evaluation (reducing computation time by 20$\times$ while keeping metrics stable). As a vehicle for validation, we introduce LUMIN (Lightweight Universal Manufacturing Inspection Network) with extreme segmentation-head compression, systematically exploring the accuracy-efficiency frontier against strong baselines. Experiments on five benchmarks demonstrate that PSP matches state-of-the-art sampling accuracy at near-random construction cost (341$\times$ faster than FPS), while inference optimizations reduce evaluation time by 20$\times$ with negligible accuracy loss.

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/2609.04775 — 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 2026-10-16T23:16:11.404Z 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).