Abstract
The efficacy of Artificial Intelligence (AI) in micro/nano manufacturing is fundamentally constrained by the scarcity of high-quality and physically grounded training data for defect inspection. Lithography defect data from semiconductor industry are rarely accessible for research use, resulting in a shortage of publicly available datasets. To address this bottleneck in lithography, this study proposes a novel methodology for generating large-scale, physically valid defect datasets with pixel-level annotations. The framework begins with the ab initio synthesis of defect layouts using controllable, physics-constrained mathematical morphology operations (erosion and dilation) applied to the original design-level layout. These synthesized layouts, together with their defect-free counterparts, are fabricated into physical samples via high-fidelity digital micromirror device (DMD)-based lithography. Optical micrographs of the synthesized defect samples and their defect-free references are then compared to create consistent defect delineation annotations. Using this methodology, we constructed a comprehensive dataset of 3,530 Optical micrographs containing 13,365 annotated defect instances including four classes: bridge, burr, pinch, and contamination. Each defect instance is annotated with a pixel-accurate segmentation mask, preserving full contour and geometry. The segmentation-based Mask R-CNN achieves AP@0.5 of 0.980, 0.965, and 0.971, compared with 0.740, 0.719, and 0.717 for Faster R-CNN on bridge, burr, and pinch classes, representing a mean AP@0.5 improvement of approximately 34%. For the contamination class, Mask R-CNN achieves an AP@0.5 roughly 42% higher than Faster R-CNN. These consistent gains demonstrate that our proposed methodology to generate defect datasets with pixel-level annotations is feasible for robust AI-based Measurement/Inspection (MI) in semiconductor fabrication.
Abstract (translated)
人工智能（AI）在微纳制造中的有效性从根本上受到高质量且具有物理基础的训练数据稀缺性的限制，尤其是在缺陷检测方面。半导体行业的光刻缺陷数据很少能用于研究用途，导致公开可用的数据集不足。为了解决这一瓶颈问题，本研究提出了一种生成大规模、物理上有效的缺陷数据集的新方法，并提供了像素级别的标注。 该框架从头开始合成缺陷布局，通过可控的数学形态学操作（腐蚀和膨胀）应用于原始设计级布局来实现这一点，这些操作受物理定律约束。随后将这些合成的布局及其无缺陷的对应物通过高保真度的数字微镜设备（DMD）基光刻技术制造成物理样本。接着比较合成缺陷样品及它们无缺陷参考的光学显微图像，以此创建一致的缺陷边界标注。 利用这种方法，我们构建了一个包含3,530张光学显微图的大规模数据集，其中记录了13,365个带注释的缺陷实例，并将其分类为四种类型：桥接、毛刺、挤压和污染。每个缺陷实例均配有像素级精确分割掩模标注，完整保留其轮廓与几何结构。 基于分割的Mask R-CNN在桥接、毛刺和挤压类别的AP@0.5分别为0.980、0.965和0.971，相较Faster R-CNN在同一类别中的表现（分别为0.740、0.719和0.717），平均AP@0.5提高了约34%。对于污染类别，Mask R-CNN的AP@0.5比Faster R-CNN高出了大约42%。 这些一致性的提升表明我们提出的生成带像素级别标注缺陷数据集的方法是可行的，这对于半导体制造中的基于AI的测量/检测（MI）具有重要意义。
URL
https://arxiv.org/abs/2512.09001
