Browse > Article
http://dx.doi.org/10.9717/kmms.2021.24.7.868

Knowledge Distillation Based Continual Learning for PCB Part Detection  

Gang, Su Myung (Dept. of Computer Engineering, Graduate School, Keimyung University)
Chung, Daewon (Mathematics Major, Faculty of Basic Sciences, Keimyung University)
Lee, Joon Jae (Faculty of Computer Engineering, Keimyung University)
Publication Information
Journal of Korea Multimedia Society / v.24, no.7, 2021 , pp. 868-879 More about this Journal
Abstract
PCB (Printed Circuit Board) inspection using a deep learning model requires a large amount of data and storage. When the amount of stored data increases, problems such as learning time and insufficient storage space occur. In this study, the existing object detection model is changed to a continual learning model to enable the recognition and classification of PCB components that are constantly increasing. By changing the structure of the object detection model to a knowledge distillation model, we propose a method that allows knowledge distillation of information on existing classified parts while simultaneously learning information on new components. In classification scenario, the transfer learning model result is 75.9%, and the continual learning model proposed in this study shows 90.7%.
Keywords
Deep Learning; PCB Inspection; Continual Learning; Knowledge Distillation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 S. Gang, N. Fabrice, and J. Lee, "Coresets for PCB Character Recognition based on Deep Learning," 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Fukuoka, Japan, 2020, pp. 637-642, 2020.
2 X. Zhou, D. Wang, and P. Krahenbuhl, "Objects as Points," arXiv preprint, arXiv:1904.07850, 2019.
3 P. Gao, R. Yuan, F. Wang, L. Xiao, H. Fujita, and Y. Zhang, "Siamese Attentional Keypoint Network for High Performance Visual Tracking," Knowledge-Based Systems, Vol. 193, pp. 1-29, 2020.
4 S. Gang and J. Lee, "Coreset Construction for Character Recognition of PCB Components Based on Deep Learning," Journal of Korea Multimedia Society, Vol. 24, No. 3, pp. 382-395, 2021.   DOI
5 K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," arXiv Preprint, arXiv:1512.03385, 2015.
6 U. Michieli and Z. Pietro, "Incremental Learning Techniques for Semantic Segmentation," Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, 2019.
7 G. Hinton, V. Oriol, and D. Jeff. "Distilling the Knowledge in a Neural Network," arXiv preprint, arXiv:1503.02531, 2015.
8 S. Park and D. Kim, "Comparison of Image Classification Performance in Convolutional Neural Network according to Transfer Learning," Journal of Korea Multimedia Society, Vol. 21 No. 12, pp. 1387-1395.   DOI
9 S. Gang, N. Fabrice, D. Chung, and J. Lee, "Character Recognition of Components Mount ed on Printed Circuit Board Using Deep Learning," Sensors, Vol. 21 No. 9, 2921, 2021.