Fusion improves chip defect detection by combining two anomaly methods
Efficient Patch-Based Anomaly Detection Fused with Diffusion Driven Generative Modeling for Semiconductor Wafer Bin Map Open Set Anomaly Detection
Machine LearningArtificial Intelligence
Summary
Detecting manufacturing defects on semiconductor wafers is hard because traditional methods either catch only small local flaws or broader unusual patterns but not both. The authors combine two approaches: one that looks at small patches of the wafer, and another that reconstructs images using a special diffusion model. By merging their outputs, the combined method spots defects more accurately than each one alone. They tested this on a large dataset of wafer images and found fewer mistakes, though they suggest smarter combination methods could improve results further.
What this means in practice
- •For semiconductor manufacturing teams: Improve detection of different types of wafer defects by combining local and global anomaly detection methods, reducing missed faults in production lines.
- •For quality control engineers in electronics factories: Use fused anomaly detection to better identify and classify yield-limiting wafer defects, enhancing overall product quality assurance.
Tested on one dataset.
Authors
Limon Bin Hossain, Md Sadib Rahman Ananta
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.