YOLOv8 for Defect Inspection of Hexagonal Directed Self-Assembly Patterns: A Data-Centric Approach
This addresses the lack of automatic defect inspection software for DSA patterns in semiconductor manufacturing, though it is incremental as it builds on existing YOLOv8 and data-centric approaches.
The paper tackles the problem of obtaining high-quality labeled datasets for defect inspection in semiconductor Directed Self-Assembly (DSA) patterns by proposing a method that minimizes expert effort, resulting in YOLOv8 achieving defect detection precisions over 0.9 mAP on the final dataset.
Shrinking pattern dimensions leads to an increased variety of defect types in semiconductor devices. This has spurred innovation in patterning approaches such as Directed self-assembly (DSA) for which no traditional, automatic defect inspection software exists. Machine Learning-based SEM image analysis has become an increasingly popular research topic for defect inspection with supervised ML models often showing the best performance. However, little research has been done on obtaining a dataset with high-quality labels for these supervised models. In this work, we propose a method for obtaining coherent and complete labels for a dataset of hexagonal contact hole DSA patterns while requiring minimal quality control effort from a DSA expert. We show that YOLOv8, a state-of-the-art neural network, achieves defect detection precisions of more than 0.9 mAP on our final dataset which best reflects DSA expert defect labeling expectations. We discuss the strengths and limitations of our proposed labeling approach and suggest directions for future work in data-centric ML-based defect inspection.