마이크로전자및패키징학회지 (Journal of the Microelectronics and Packaging Society)

  • 제30권4호
  • /
  • Pages.69-78
  • /
  • 2023
  • /
  • 1226-9360(pISSN)
  • /
  • 2287-7525(eISSN)
한국마이크로전자및패키징학회 (The Korean Microelectronics and Packaging Society)
권호 표지
DOI QR코드

DOI QR Code

MAGICal Synthesis: 반도체 패키지 이미지 생성을 위한 메모리 효율적 접근법

MAGICal Synthesis: Memory-Efficient Approach for Generative Semiconductor Package Image Construction

  • Yunbin Chang (School of Computer Engineering, Hansung University) ;
  • Wonyong Choi (R&D Center, Genesem) ;
  • Keejun Han (School of Computer Engineering, Hansung University)
  • 투고 : 2023.12.15
  • 심사 : 2023.12.29
  • 발행 : 2023.12.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

산업 인공지능의 발달과 함께 반도체의 수요가 크게 증가하고 있다. 시장 수요에 대응하기 위해 패키징 공정에서 자동 결함 검출의 중요성 역시 증가하고 있다. 이에 따라, 패키지의 자동 불량 검사를 위한 딥러닝 기반의 방법론들의 연구가 활발히 이루어 지고 있다. 딥러닝 기반의 모델은 학습을 위해서 대량의 고해상도 데이터를 필요로 하나, 보안이 중요한 반도체 분야의 특성상 관련 데이터의 공유 및 레이블링이 쉽지 않아 모델의 학습이 어려운 한계를 지니고 있다. 또한 고해상도 이미지를 생성하기 위해 상당한 컴퓨팅 자원이 요구되는데, 본 연구에서는 분할정복 접근법을 통해 적은 컴퓨팅 자원으로 딥러닝 모델 학습을 위한 충분한 양의 데이터를 확보하는 방법을 소개한다. 제안된 방법은 높은 해상도의 이미지를 분할하고 각 영역에 조건 레이블을 부여한 후, 독립적인 부분 영역과 경계를 학습시켜, 경계 손실이 일관적인 이미지를 생성하도록 유도한다. 이후, 분할된 이미지를 하나로 통합하여, 최종적으로 모델이 고해상도의 이미지를 생성하도록 구성하였다. 실험 결과, 본 연구를 통해 증강된 이미지들은 높은 효율성, 일관성, 품질 및 범용성을 보였다.

With the rapid growth of artificial intelligence, the demand for semiconductors is enormously increasing everywhere. To ensure the manufacturing quality and quantity simultaneously, the importance of automatic defect detection during the packaging process has been re-visited by adapting various deep learning-based methodologies into automatic packaging defect inspection. Deep learning (DL) models require a large amount of data for training, but due to the nature of the semiconductor industry where security is important, sharing and labeling of relevant data is challenging, making it difficult for model training. In this study, we propose a new framework for securing sufficient data for DL models with fewer computing resources through a divide-and-conquer approach. The proposed method divides high-resolution images into pre-defined sub-regions and assigns conditional labels to each region, then trains individual sub-regions and boundaries with boundary loss inducing the globally coherent and seamless images. Afterwards, full-size image is reconstructed by combining divided sub-regions. The experimental results show that the images obtained through this research have high efficiency, consistency, quality, and generality.

키워드

과제정보

This work was supported by the Technology Innovation Program (No. 20022899, Development of AI-based smart manufacturing process and equipment technology to strengthen the competitiveness of semiconductor materials, parts, and equipment) funded by the Ministry of Trade, Industry and Energy (MOTIE, Republic of Korea).

참고문헌

  1. T. Y. Kang and T. S. Kim, "Signal-Based Fault Detection and Diagnosis on Electronic Packaging and Applications of Artificial Intelligence Techniques", J. Microelectron. Packag. Soc., 30(1), 30-41 (2023).
  2. H. J. Kim and J. P. Jung, "Artificial Intelligence Semiconductor and Packaging Technology Trend", J. Microelectron. Packag. Soc., 30(3), 11-19 (2023).
  3. D. W. Park and M. H. Yu, "A Study on Effect of Pad Design on Assembly and Adhesion Reliability of Surface Mount Technology (SMT)", J. Microelectron. Packag. Soc., 29(3), 31-35 (2022).
  4. B. Dey, D. Goswami, S. Halder, K. Khalil, P. Leray, and M. A. Bayoumi, "Deep Learning-Based Defect Classification and Detection in SEM Images", in Metrology, Inspection, and Process Control XXXVI, SPIE, p. PC120530Y (2022).
  5. V. De Ridder, B. Dey, S. Halder, and B. Van Waeyenberge, "SEMI-DiffusionInst: A Diffusion Model Based Approach for Semiconductor Defect Classification and Segmentation", 2023 International Symposium ELMAR, IEEE, 61-66 (2023).
  6. T. Karras, T. Aila, S. Laine, and J. Lehtinen, "Progressive Growing of GANs for Improved Quality, Stability, and Variation", arXiv preprint arXiv:1710.10196 (2017)
  7. S. P. Porkodi, V. Sarada, V. Maik, and K. Gurushankar, "Generic Image Application Using GANs (Generative Adversarial Networks): A Review", Evolving Systems, 14(5), 903-917 (2023). https://doi.org/10.1007/s12530-022-09464-y
  8. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, and Y. Bengio, "Generative Adversarial Nets", Advances in Neural Information Processing Systems, 27 (2014).
  9. M. Mirza and S. Osindero, "Conditional Generative Adversarial Nets", arXiv preprint arXiv:1411.1784 (2014).
  10. A. Odena, C. Olah, and J. Shlens, "Conditional Image Synthesis with Auxiliary Classifier GANs", in International Conference on Machine Learning, PMLR, 2642-2651 (2017).
  11. A. Radford, L. Metz, and S. Chintala, "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks", arXiv preprint arXiv:1511.06434 (2015).
  12. H. Liu, B. Li, H. Wu, H. Liang, Y. Huang, Y. Li, and Y. Zheng, "Combating Mode Collapse in GANs via Manifold Entropy Estimation", arXiv preprint arXiv:2208.12055 (2022).
  13. M. Arjovsky, S. Chintala, and L. Bottou, "Wasserstein Generative Adversarial Networks", in International Conference on Machine Learning, PMLR, 214-223 (2017).
  14. I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. C. Courville, "Improved Training of Wasserstein GANs", Advances in Neural Information Processing Systems, 30 (2017).
  15. H. Zhang, I. Goodfellow, D. Metaxas, A. Odena, "Self-Attention Generative Adversarial Networks", in International Conference on Machine Learning, PMLR, 7354-7363 (2019).
  16. A. Brock, J. Donahue, and K. Simonyan, "Large Scale GAN Training for High Fidelity Natural Image Synthesis", arXiv preprint arXiv:1809.11096 (2018).
  17. P. Isola, J. Y. Zhu, T. Zhou, and A. A. Efros, "Image-to-Image Translation with Conditional Adversarial Networks", in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1125-1134 (2017).
  18. W. Cheng, M. Zhao, Z. Ye, and S. Gu, "MFAGAN: A Compression Framework for Memory-Efficient On-Device Super-Resolution GAN", arXiv preprint arXiv:2107.12679 (2021).
  19. D. Tantawy, M. Zahran, and A. Wassal, "A Survey on GAN Acceleration Using Memory Compression Techniques", Journal of Engineering and Applied Science, 68, 1-23 (2021). https://doi.org/10.1186/s44147-021-00003-1
  20. K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition", in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770-778 (2016).
  21. Y. Gao, Y. Liu, H. Zhang, Z. Li, Y. Zhu, H. Lin, M. Yang, "Estimating GPU Memory Consumption of Deep Learning Models", in Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 1342-1352 (2020).
  22. M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, "GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium", Advances in Neural Information Processing Systems, 30 (2017).
  23. T. Karras, S. Laine, and T. Aila, "A Style-Based Generator Architecture for Generative Adversarial Networks", in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 4401-4410 (2019).