arXiv：cs.LG· Limon Bin Hossain, Md Sadib Rahman Ananta·· 4 小时前AI 评分30
基于 Patch 的 EfficientAD 与扩散模型融合：半导体晶圆 Bin Map 开放集异常检测
Efficient Patch-Based Anomaly Detection Fused with Diffusion Driven Generative Modeling for Semiconductor Wafer Bin Map Open Set Anomaly Detection
AI 导读
该研究提出一种混合单类框架，将基于 patch 的 student-teacher 检测器 EfficientAD 与用于部分扩散重建的 DDPM 耦合，通过固定凸组合融合二者百分位校准分数。
正文
Abstract: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.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.09993 [cs.LG] |
| (or arXiv:2610.09993v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09993 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Limon Bin Hossain [view email]
[v1]
Wed, 7 Oct 2026 12:52:58 UTC (1,254 KB)
来源：arXiv：cs.LG · arxiv.org