DECOR通过旋转鲁棒性提升晶圆缺陷聚类精度，无需人工调参。
DECOR: Deep Embedding Clustering with Orientation Robustness
- 引入旋转不变的深度聚类框架，自动处理晶圆图的方位差异。
- 在MixedWM38数据集上实现无监督聚类，准确率优于现有方法。
- 适合半导体质检场景，尤其适用于多缺陷、不平衡数据。
在半导体制造中，早期检测晶圆缺陷对提升良品率至关重要。然而，来自晶圆质量测试的原始数据通常复杂、未标注、分布不均，且单个晶圆可能包含多种缺陷，因此需设计在不完美数据条件下仍可靠的聚类方法。本文提出DECOR——一种具备方向鲁棒性的深度聚类框架，可将复杂的缺陷模式从晶圆图中聚类为一致类别。我们在开源的MixedWM38数据集上评估该方法，证明其能在无需人工调参的情况下发现有效聚类。DECOR显式考虑晶圆图的方向变化，确保空间相似的缺陷无论旋转或对齐如何，都能被一致分组。实验表明，该方法显著优于现有聚类基线，为自动化视觉检测系统提供了可靠且可扩展的解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。