在現今的積體電路技術發展下，製程節點隨著發展一直縮小，
使得電路密度越來越大，這項發展讓熱點偵測技術需要以更快的
速度來執行以應付數量日漸龐大的電路結構。在現實中，通常想
要發現熱點的方法就是實際經過製程再透過電子顯微鏡去拍攝，
但在技術發展下，使用人力來達成這項工作將會越來越不可行。
所以本論文透過深度學習技術來解決此問題，我們的模型主要分
成兩部分: 首先透過物件偵測方法切入問題，使用了一階的物件偵
測模型使偵測器在速度加快的情況下還能維持好的準確度，再輔
以電路變化預測模型，讓我們能得知電路的預測變化方向，使我
們的模型的物件特徵再進一步得到加強。同時，為了更好的融合
兩者間的特徵，我們使用了跨域關注的方法來進行融合。實驗顯
示我們的方法不管是在模擬的資料上或是真實的資料上都有著相
當不錯的表現，在後續研究也證明了我們設計的融合模組的有效
性。
關鍵字: 熱點偵測、物件偵測、多模型融合、曝光模擬、跨域
關注

Recent advances in VLSI fabrication technology have resulted in die shrink and layout density enlargement, leading an urgent need for advanced hotspot detection methods.
These advances makes the hotspot detection technology need to be executed at a faster speed to cope with the increasing number of layout structures. These advances makes the hotspot detection technology need to be executed at a faster speed to cope with the increasing number of layout structures. Recently, machine learning methods shows the power on these problems. But existing hotspot detectors has some weak points, they consider only layout information, real process has more uncertainty effect to the hotspots. Thus, real world information is also needs to be taken into account.
Therefore, this paper solves this problem through deep learning technology. Our model is mainly divided into two parts: first, we cut into the problem through the object detection method, the Retinanet object detection model is proved to make the detector maintain good accuracy while accelerating the speed, and then supported by the layout change prediction model, Lithonet, so that we can know the predicted deformation of the layout so that the object detection features of our model are further strengthened. At the same time, in order to better integrate the features between the two, we use a cross-domain attention method for fusion. Experiments show that our method performs well both on simulated data and real-world data. In the ablation study, also proves the effectiveness of the fusion module we designed.
Index Terms — Hotspot detection, Object detection, Multi-model fusion, Lithography simulator, cross-attention

References
[1] Y. Jiang, F. Yang, B. Yu, D. Zhou, and X. Zeng, “Efficient layout hotspot detection via
binarized residual neural network ensemble,” IEEE Transactions on Computer-Aided De-
sign of Integrated Circuits and Systems, vol. 40, no. 7, pp. 1476–1488, 2021.
[2] H. Geng, H. Yang, L. Zhang, J. Miao, F. Yang, X. Zeng, and B. Yu, “Hotspot detection
via attention-based deep layout metric learning,” in 2020 IEEE/ACM International Con-
ference On Computer Aided Design (ICCAD), pp. 1–8, 2020.
[3] H. Yang, J. Su, Y. Zou, B. Yu, and E. F. Young, “Layout hotspot detection with feature
tensor generation and deep biased learning,” in Proceedings of the 54th Annual Design
Automation Conference 2017, pp. 1–6, 2017.
[4] R. Chen, W. Zhong, H. Yang, H. Geng, X. Zeng, and B. Yu, “Faster region-based hotspot
detection,” in Proceedings of the 56th Annual Design Automation Conference 2019, pp. 1–
6, 2019.
[5] T. Gai, T. Qu, S. Wang, X. Su, R. Xu, Y. Wang, J. Xue, Y. Su, Y. Wei, and T. Ye,
“Flexible hotspot detection based on fully convolutional network with transfer learning,”
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 41,
no. 11, pp. 4626–4638, 2021.
[6] B. Zhu, R. Chen, X. Zhang, F. Yang, X. Zeng, B. Yu, and M. D. Wong, “Hotspot detec-
tion via multi-task learning and transformer encoder,” in 2021 IEEE/ACM International
Conference On Computer Aided Design (ICCAD), pp. 1–8, IEEE, 2021.
[7] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and
I. Polosukhin, “Attention is all you need,” Advances in neural information processing
systems, vol. 30, 2017.
[8] K. Qian, S. Zhu, X. Zhang, and L. E. Li, “Robust multimodal vehicle detection in foggy
weather using complementary lidar and radar signals,” in Proceedings of the IEEE/CVF
Conference on Computer Vision and Pattern Recognition, pp. 444–453, 2021.
[9] X. Lin, J. Pan, J. Xu, Y. Chen, and C. Zhuo, “Lithography hotspot detection via hetero-
geneous federated learning with local adaptation,” in 2022 27th Asia and South Pacific
Design Automation Conference (ASP-DAC), pp. 166–171, IEEE, 2022.
[10] R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate
object detection and semantic segmentation,” in Proceedings of the IEEE conference on
computer vision and pattern recognition, pp. 580–587, 2014.
[11] R. Girshick, “Fast r-cnn,” in Proceedings of the IEEE international conference on com-
puter vision, pp. 1440–1448, 2015.
[12] S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detec-
tion with region proposal networks,” Advances in neural information processing systems,
vol. 28, 2015.
[13] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-
time object detection,” in Proceedings of the IEEE conference on computer vision and
pattern recognition, pp. 779–788, 2016.
[14] J. Redmon and A. Farhadi, “Yolo9000: better, faster, stronger,” in Proceedings of the IEEE
conference on computer vision and pattern recognition, pp. 7263–7271, 2017.
[15] J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” arXiv preprint
arXiv:1804.02767, 2018.
[16] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “Ssd:
Single shot multibox detector,” in European conference on computer vision, pp. 21–37,
Springer, 2016.
[17] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detec-
tion,” in Proceedings of the IEEE international conference on computer vision, pp. 2980–
2988, 2017.
[18] H.-C. Shao, C.-Y. Peng, J.-R. Wu, C.-W. Lin, S.-Y. Fang, P.-Y. Tsai, and Y.-H. Liu, “From
ic layout to die photograph: A cnn-based data-driven approach,” IEEE Transactions on
Computer-Aided Design of Integrated Circuits and Systems, vol. 40, no. 5, pp. 957–970,
2021.
[19] H.-C. Shao, H.-L. Ping, K.-s. Chen, W.-T. Su, C.-W. Lin, S.-Y. Fang, P.-Y. Tsai, and Y.-H.
Liu, “Keeping deep lithography simulators updated: Global-local shape-based novelty de-
tection and active learning,” IEEE Transactions on Computer-Aided Design of Integrated
Circuits and Systems, pp. 1–1, 2022.
[20] O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedi-
cal image segmentation,” in International Conference on Medical image computing and
computer-assisted intervention, pp. 234–241, Springer, 2015.
[21] T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid
networks for object detection,” in Proceedings of the IEEE conference on computer vision
and pattern recognition, pp. 2117–2125, 2017.
[22] Z. Zheng, P. Wang, W. Liu, J. Li, R. Ye, and D. Ren, “Distance-iou loss: Faster and better
learning for bounding box regression,” in Proceedings of the AAAI conference on artificial
intelligence, vol. 34, pp. 12993–13000, 2020.