Accurate lithography hotspot detection using deep convolutional neural networks

Abstract. As the physical design of semiconductors continues to shrink, the lithography process is becoming more sensitive to layout design. Identifying lithography hotspots (HSs) in the layout design stage appears to be more and more crucial for fast semiconductor development. In this direction, we propose an accurate HS detection method using convolutional neural networks. Our approach produces more accurate detection performance (95.5% recall and 22.2% precision) compared to previous approaches. In spite of the use of deep convolutional neural networks, our method achieves a fast detection time of 0.72  h/mm2. In order to quickly and accurately detect HSs, we not only utilize the nature of convolutional-neural networks but also make additional technical efforts to improve the performance of our framework, including inspection region reduction, data augmentation, DBSCAN clustering, modified batch normalization, and fast image scanning. To the best of our knowledge, our approach is the first CNN-based lithography HS detection.