DECOR: Deep Embedding Clustering with Orientation Robustness
This work addresses the need for reliable and scalable automated visual inspection in semiconductor manufacturing, though it appears incremental as it builds on existing deep clustering methods with a focus on orientation robustness.
The paper tackled the problem of clustering complex and unlabeled wafer defect patterns in semiconductor manufacturing by introducing DECOR, a deep clustering framework with orientation robustness, which outperformed existing baselines on the MixedWM38 dataset.
In semiconductor manufacturing, early detection of wafer defects is critical for product yield optimization. However, raw wafer data from wafer quality tests are often complex, unlabeled, imbalanced and can contain multiple defects on a single wafer, making it crucial to design clustering methods that remain reliable under such imperfect data conditions. We introduce DECOR, a deep clustering with orientation robustness framework that groups complex defect patterns from wafer maps into consistent clusters. We evaluate our method on the open source MixedWM38 dataset, demonstrating its ability to discover clusters without manual tuning. DECOR explicitly accounts for orientation variations in wafer maps, ensuring that spatially similar defects are consistently clustered regardless of its rotation or alignment. Experiments indicate that our method outperforms existing clustering baseline methods, thus providing a reliable and scalable solution in automated visual inspection systems.