請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/99714完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 李家岩 | zh_TW |
| dc.contributor.advisor | Chia-Yen Lee | en |
| dc.contributor.author | 賴毅愷 | zh_TW |
| dc.contributor.author | I-Kai Lai | en |
| dc.date.accessioned | 2025-09-17T16:27:38Z | - |
| dc.date.available | 2025-09-18 | - |
| dc.date.copyright | 2025-09-17 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-08-05 | - |
| dc.identifier.citation | Abeysundara, H. A., Hamori, H., Matsui, T., & Sakawa, M. (2014). Defects Detection of TFT Lines of Flat Panel Displays Using an Evolutionary Optimized Recurrent Neural Network. American Journal of Operations Research, 04(03), 113–123.
Bai, J., Liu, Z., Wang, H., Chen, R., Mu, L., Li, X., Zhou, J. T., Feng, Y., Wu, J., & Hu, H. (2023). Towards Distribution-Agnostic Generalized Category Discovery. Advances in Neural Information Processing Systems, 36, 58625–58647. Bendale, A., & Boult, T. (2015). Towards Open World Recognition. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1893–1902. Cao, K., Brbic, M., & Leskovec, J. (2022). Open-World Semi-Supervised Learning. Proceedings of the International Conference on Learning Representations. Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised Learning of Visual Features by Contrasting Cluster Assignments. Advances in Neural Information Processing Systems, 33, 9912–9924. Chang, Y.-C., Chang, K.-H., Meng, H.-M., & Chiu, H.-C. (2022). A Novel Multicategory Defect Detection Method Based on the Convolutional Neural Network Method for TFT-LCD Panels. Mathematical Problems in Engineering, 2022(1), 6505372. Chen, S., Zhang, Y., Yi, M., Ma, J., & Hou, X. (2021). Wafer maps defect recognition based on transfer learning of handwritten pre-training network. 2021 International Symposium on Computer Technology and Information Science (ISCTIS), 280–283. Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the 37th International Conference on Machine Learning, 1597–1607. Chen, Y., Zhu, X., Li, W., & Gong, S. (2020). Semi-Supervised Learning under Class Distribution Mismatch. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 3569–3576. Chien, C.-F., Ling, Y.-M., Kao, S.-X., & Lin, C.-H. (2022). Image-Based Defect Classification for TFT-LCD Array via Convolutional Neural Network. IEEE Transactions on Semiconductor Manufacturing, 35(4), 650–657. Chou, C.-W., Chien, C.-F., & Gen, M. (2014). A Multiobjective Hybrid Genetic Algorithm for TFT-LCD Module Assembly Scheduling. IEEE Transactions on Automation Science and Engineering, 11(3), 692–705. Ding, L., Li, C., Jin, D., & Ding, S. (2024). Survey of spectral clustering based on graph theory. Pattern Recognition, 151, 110366. Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., & Zisserman, A. (2021). With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 9568–9577. Gui, Q., Zhou, H., Guo, N., & Niu, B. (2024). A survey of class-imbalanced semi-supervised learning. Machine Learning, 113(8), 5057–5086. Guo, L.-Z., Zhang, Z.-Y., Jiang, Y., Li, Y.-F., & Zhou, Z.-H. (2020). Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data. Proceedings of the 37th International Conference on Machine Learning, 3897–3906. Gupta, K., Ajanthan, T., Hengel, A. van den, & Gould, S. (2022). Understanding and Improving the Role of Projection Head in Self-Supervised Learning. arXiv preprint, arXiv:2212.11491. Han, K., Rebuffi, S.-A., Ehrhardt, S., Vedaldi, A., & Zisserman, A. (2020). Automatically Discovering and Learning New Visual Categories with Ranking Statistics. Proceedings of the International Conference on Learning Representations (ICLR). He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum Contrast for Unsupervised Visual Representation Learning. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9726–9735. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. Heydari, A. A., Thompson, C. A., & Mehmood, A. (2019). SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions. arXiv preprint, arXiv:1912.12355. Hong, T.-Y., & Chien, C.-F. (2020). A simulation-based dynamic scheduling and dispatching system with multi-criteria performance evaluation for Industry 3.5 and an empirical study for sustainable TFT-LCD array manufacturing. International Journal of Production Research, 58(24), 7531–7547. Hsieh, T.-T., Hsiao, J.-H., Lee, C.-Y., & Wang, H.-K. (2025). Unsupervised Image Demoirèing With Self-Consistent GAN for TFT-LCD Defect Recognition. IEEE Transactions on Semiconductor Manufacturing, 1–1. Islam, A., Chen, C.-F., Panda, R., Karlinsky, L., Radke, R., & Feris, R. (2021). A Broad Study on the Transferability of Visual Representations with Contrastive Learning. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 8825–8835. Jazi, A. Y., Liu, J. J., & Lee, H. (2012). Automatic Inspection of TFT-LCD Glass Substrates Using Optimized Support Vector Machines. IFAC Proceedings Volumes, 45(15), 325–330. Kahng, H., & Kim, S. B. (2021). Self-Supervised Representation Learning for Wafer Bin Map Defect Pattern Classification. IEEE Transactions on Semiconductor Manufacturing, 34(1), 74–86. Kang, S. B., Lee, J. H., Song, K. Y., & Pahk, H. J. (2009). Automatic defect classification of TFT-LCD panels using machine learning. 2009 IEEE International Symposium on Industrial Electronics, 2175–2177. Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., & Krishnan, D. (2020). Supervised Contrastive Learning. Advances in Neural Information Processing Systems, 33, 18661–18673. Kim, M., Lee, M., An, M., & Lee, H. (2020). Effective automatic defect classification process based on CNN with stacking ensemble model for TFT-LCD panel. Journal of Intelligent Manufacturing, 31(5), 1165–1174. Kuhn, H. W. (1955). The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1–2), 83–97. Liu, J., Wang, Y., Zhang, T., Fan, Y., Yang, Q., & Shao, J. (2023). Open-world Semi-supervised Novel Class Discovery. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 4002–4010. Liu, Y.-H., Wang, C.-K., Ting, Y., Lin, W.-Z., Kang, Z.-H., Chen, C.-S., & Hwang, J.-S. (2009). In-TFT-Array-Process Micro Defect Inspection Using Nonlinear Principal Component Analysis. International Journal of Molecular Sciences, 10(10), Article 10. Lu, H.-P., & Su, C.-T. (2021). CNNs Combined With a Conditional GAN for Mura Defect Classification in TFT-LCDs. IEEE Transactions on Semiconductor Manufacturing, 34(1), 25–33. Ma, L., Liu, W., Liu, Y., & Jiang, H. (2013). An Automatic Detection Algorithm for Surface Defects in TFT-LCD. Proceedings of the 2013 2nd IAPR Asian Conference on Pattern Recognition, 847–851. Niu, S., Lin, L., Huang, J., & Wang, C. (2024). OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning. Advances in Neural Information Processing Systems, 37, 99836–99866. Oliver, A., Odena, A., Raffel, C. A., Cubuk, E. D., & Goodfellow, I. (2018). Realistic Evaluation of Deep Semi-Supervised Learning Algorithms. Advances in Neural Information Processing Systems, 31. Park, S., Kwon, H., Sohn, K., & Lee, K. (2024). Rethinking Open-World Semi-Supervised Learning: Distribution Mismatch and Inductive Inference. arXiv preprint, arXiv:2405.20829. Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning Transferable Visual Models From Natural Language Supervision. Proceedings of the 38th International Conference on Machine Learning, 8748–8763. Rizve, M. N., Kardan, N., Khan, S., Shahbaz Khan, F., & Shah, M. (2022). OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning. Proceedings of the European Conference on Computer Vision, 382–401. Rizve, M. N., Kardan, N., & Shah, M. (2022). Towards Realistic Semi-supervised Learning. In S. Avidan, G. Brostow, M. Cissé, G. M. Farinella, & T. Hassner (Eds.), Computer Vision – ECCV 2022 (Vol. 13691, pp. 437–455). Scheirer, W. J., de Rezende Rocha, A., Sapkota, A., & Boult, T. E. (2013). Toward Open Set Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(7), 1757–1772 Shen, P.-C., & Lee, C.-Y. (2022). Wafer Bin Map Recognition With Autoencoder-Based Data Augmentation in Semiconductor Assembly Process. IEEE Transactions on Semiconductor Manufacturing, 35(2), 198–209. Sun, X., Yang, Z., Zhang, C., Ling, K.-V., & Peng, G. (2020). Conditional Gaussian Distribution Learning for Open Set Recognition. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 13477–13486. Sun, Y., & Li, Y. (2023). OpenCon: Open-World Contrastive Learning. Transactions on Machine Learning Research. Tzu, F.-M. (2021). Effectiveness of Electrical and Optical Detection at Pixel Circuit on Thin-Film Transistors. Micromachines, 12(2), 135. Tzu, F.-M., Chen, J.-S., & Hsu, S.-H. (2021). Detection of Electrical Circuit in a Thin-Film-Transistor Liquid-Crystal Display Using a Hybrid Optoelectronic Apparatus: An Array Tester and Automatic Optical Inspection. Micromachines, 12(8), 964. Vaze, S., Hant, K., Vedaldi, A., & Zisserman, A. (2022). Generalized Category Discovery. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7482–7491. Wang, J., Xu, C., Yang, Z., Zhang, J., & Li, X. (2020). Deformable Convolutional Networks for Efficient Mixed-Type Wafer Defect Pattern Recognition. IEEE Transactions on Semiconductor Manufacturing, 33(4), 587–596. Xia, Y., Luo, C., Jia, L., & Zhou, Y. (2022). Defect Detection Algorithm for TFT-LCD Circuits Based on Modified YOLOX Model. 2022 5th International Conference on Mechatronics, Robotics and Automation (ICMRA), 139–145. Xue, Y., Gan, E., Ni, J., Joshi, S., & Mirzasoleiman, B. (2024). Investigating the Benefits of Projection Head for Representation Learning, arXiv preprint, arXiv:2403.11391. Yang, H., Mei, S., Song, K., Tao, B., & Yin, Z. (2018). Transfer-Learning-Based Online Mura Defect Classification. IEEE Transactions on Semiconductor Manufacturing, 31(1), 116–123. Zhang, Y., & Zhang, J. (2005). Fuzzy recognition of the defect of TFT-LCD. Electronic Imaging and Multimedia Technology IV, 5637, 233–240. Zhong, Z., Zhu, L., Luo, Z., Li, S., Yang, Y., & Sebe, N. (2021). OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in an Open World. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9457–9465. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/99714 | - |
| dc.description.abstract | 在TFT-LCD面板製造過程中，缺陷模式的偵測與分類是具高度挑戰性的任務。儘管近年深度學習技術已廣泛應用於自動缺陷分類，現有方法大多聚焦於對已知模式的分類，忽略了實際應用中可能遇到且需要分類的新穎缺陷模式。此外，傳統方法亦面臨數據稀少、標註不足與類別不平衡等問題，進一步限制這些方法在製造現場的實用性。為了解決上述限制，本研究提出一個針對TFT-LCD電性缺陷的開路/短路測試圖（TOS map）之二階段缺陷分類框架。第一階段使用來自半導體製程的晶圓圖進行對比式預訓練，以在有限的TOS map數據下提升分類效果。隨後採用新穎的雙分支開放世界半監督學習方法，穩健地處理類別不平衡和新穎缺陷模式的辨識問題。本研究以業界專家驗證的模擬TOS map資料集驗證方法論，結果顯示本方法在兩種實務情境下皆展現優良的效力，分別達到 98.5% 與 99.2% 的總分類準確率。與基準方法ORCA（搭配本研究提出之預訓練策略）相比，所提出的開放世界半監督學習方法在兩情境分別提升 10.7% 與 52.0% 的準確率，同時具有較低的分類變異，驗證了該方法在TFT-LCD製造智慧品質控制中的有效性。 | zh_TW |
| dc.description.abstract | Defect pattern detection and classification present significant challenges in thin-film transistor liquid-crystal display (TFT-LCD) manufacturing. While deep learning techniques have advanced automatic defect classification, most methods focus on known defect patterns, neglecting novel defect patterns that may be encountered in practical applications and require classification. Moreover, traditional approaches struggle with data scarcity, insufficient labeling, and class imbalance. To address these limitations, this study proposes a two-stage defect classification framework for Test for Open/Short (TOS) maps, which measure electrical defects. Specifically, our two-stage framework begins with contrastive pre-training on semiconductor manufacturing wafer bin maps to enhance classification with limited TOS data, followed by a novel dual-branch open-world SSL methodology that robustly handles both class imbalance and novel pattern discovery. Experimental validation on industry-validated synthetic TOS datasets demonstrates superior performance across two practical scenarios, achieving total accuracies of 98.5% and 99.2%. Compared to the baseline ORCA (with our pretraining strategy), the proposed approach yields accuracy improvements of 10.7% and 52.0%, with reduced variance, validating its effectiveness for intelligent quality control in TFT-LCD manufacturing. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-09-17T16:27:38Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-09-17T16:27:38Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 謝辭 i
摘要 ii Abstract iii Contents iv List of Figures vi List of Tables vii 1 Introduction 1 1.1 Background and Motivation 1 1.2 Research Objective 6 1.3 Thesis Architecture 9 2 Literature Review 10 2.1 TFT-LCD Defect Classification 10 2.2 Contrastive Learning 15 2.3 Open World Semi-Supervised Learning 17 2.4 Summary and Discussion 20 3 Methodology 22 3.1 Research Framework 22 3.2 Contrastive Representation Learning Pre-Training 24 3.2.1 Overview of Contrastive Representation Learning 24 3.2.2 SimCLR Pre-Training 24 3.3 Open-World Semi-Supervised Learning 26 3.3.1 Problem Statement and Setup 26 3.3.2 Methodology Architecture 27 3.3.3 Contrastive Learning Branch 28 3.3.3.1 Branch Architecture 29 3.3.3.2 Pseudo-Label Guided Contrastive Loss 30 3.3.3.3 Distribution Estimation 31 3.3.4 Open-world Semi-supervised Learning Branch 32 3.3.4.1 Branch Architecture 32 3.3.4.2 Supervised and Pairwise Objectives 33 3.3.4.3 Regularize Predictions with Semantic Distribution Estimation 35 3.3.4.4 Contrastive Loss 37 4 Empirical Study 39 4.1 Experiment Setting 39 4.1.1 Dataset Collection 39 4.1.2 Experimental Scenarios 41 4.1.3 Implementation Details 42 4.2 Evaluation 43 4.2.1 Evaluation Metrics 43 4.2.2 Experiment Result 44 5 Conclusion and Future Work 63 5.1 Conclusion 63 5.2 Future Work 64 Reference 67 Appendix 76 Appendix A – Additional Results 76 Appendix B – Synthetic Data Generation Procedure 85 | - |
| dc.language.iso | en | - |
| dc.subject | 開放世界半監督學習 | zh_TW |
| dc.subject | 缺陷分類 | zh_TW |
| dc.subject | TFT-LCD | zh_TW |
| dc.subject | 遷移學習 | zh_TW |
| dc.subject | 對比式學習 | zh_TW |
| dc.subject | Transfer learning | en |
| dc.subject | Contrastive learning | en |
| dc.subject | Open-world semi-supervised learning | en |
| dc.subject | Defect classification | en |
| dc.subject | TFT-LCD | en |
| dc.title | 半導體晶圓圖遷移學習於開放世界半監督學習之 TFT-LCD 電性測試缺陷分類 | zh_TW |
| dc.title | Defect Classification for TFT-LCD Electrical Test by Contrastive-Based Open-World Semi-Supervised Learning with Transfer Learning from Semiconductor Wafer Maps | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 孫紹華;陳以錚;藍俊宏 | zh_TW |
| dc.contributor.oralexamcommittee | Shao-Hua Sun;Yi-Cheng Chen;Jakey Blue | en |
| dc.subject.keyword | 缺陷分類,開放世界半監督學習,TFT-LCD,對比式學習,遷移學習, | zh_TW |
| dc.subject.keyword | Defect classification,Open-world semi-supervised learning,TFT-LCD,Contrastive learning,Transfer learning, | en |
| dc.relation.page | 86 | - |
| dc.identifier.doi | 10.6342/NTU202503196 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2025-08-08 | - |
| dc.contributor.author-college | 管理學院 | - |
| dc.contributor.author-dept | 資訊管理學系 | - |
| dc.date.embargo-lift | 2028-08-01 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf 此日期後於網路公開 2028-08-01 | 4.28 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。