Metraipolis › archive › dc_889b4060a151

Efficient Patch-Based Anomaly Detection Fused with Diffusion Driven Generative Modeling for Semiconductor Wafer Bin Map Open Set Anomaly Detection — arXiv:2610.09993

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09993
License (as archived)
CC0-1.0
Archived
2026-10-08T11:11:41.744Z
SHA-256 of the archived text
e58f6dffa80d9c433bf0676b3c22cdf25dd12b6dac7cb59bb835016a08934132
Stable URL of this page
https://metraipolis.com/documento/dc_889b4060a151

How to cite

Efficient Patch-Based Anomaly Detection Fused with Diffusion Driven Generative Modeling for Semiconductor Wafer Bin Map Open Set Anomaly Detection — arXiv:2610.09993 — arXiv (en), https://arxiv.org/abs/2610.09993 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_889b4060a151 (Metraipolis archive dc_889b4060a151, sha256 e58f6dffa80d9c433bf0676b3c22cdf25dd12b6dac7cb59bb835016a08934132)
BibTeX
@misc{dc889b4060a151,
  title = {Efficient Patch-Based Anomaly Detection Fused with Diffusion Driven Generative Modeling for Semiconductor Wafer Bin Map Open Set Anomaly Detection — arXiv:2610.09993},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09993},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_889b4060a151; sha256 e58f6dffa80d9c433bf0676b3c22cdf25dd12b6dac7cb59bb835016a08934132},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09993. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spatial defect signatures on wafer bin maps (WBMs) trace yield loss to specific process faults, yet supervised classifiers recognize only the defect types seen during training, and one-class detectors built on a single mechanism tend to capture either local structural deviations or global distributional violations, but rarely both. This work proposes a hybrid one-class framework that couples a patch-based student-teacher detector (EfficientAD) with a denoising diffusion probabilistic model (DDPM) used for partial-diffusion reconstruction, and fuses their percentile-calibrated scores through a fixed convex combination. Trained on only 700 normal wafers from the WM-38K mixed-type dataset and evaluated on 18,658 held-out wafers, the fused detector reached an AUROC of 0.9985 and reduced misclassifications from 852 (DDPM) and 1,412 (EfficientAD) to 618, with all pairwise differences significant at p < 0.001. Beyond aggregate accuracy, the analysis shows that the gain arises from weakly overlapping errors between the two modules, yet fixed-weight fusion recovers only 40-70% of the correction available to an oracle selector. Under the benchmark's inverted class balance, average precision and F1 saturate, while the Matthews correlation coefficient and negative predictive value expose unreliable normal predictions. Pixel-level maps further show that strong image-level separability does not imply spatial localization, and the diffusion module succeeds as a local density prior rather than through global geometric reasoning. These findings motivate sample-adaptive fusion and imbalance-aware evaluation of hybrid wafer anomaly detectors.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.09993 — 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 2026-10-08T10:14:06.145Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).