請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88009
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 賴飛羆 | zh_TW |
dc.contributor.advisor | Fei-Pei Lai | en |
dc.contributor.author | 楊雅貽 | zh_TW |
dc.contributor.author | Ya-Yi Yang | en |
dc.date.accessioned | 2023-08-01T16:22:44Z | - |
dc.date.available | 2023-11-09 | - |
dc.date.copyright | 2023-08-01 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-07-05 | - |
dc.identifier.citation | Antunes, Rodolfo Stoffel, Cristiano André da Costa, Arne Küderle, Imrana Abdullahi Yari, and Björn Eskofier. "Federated learning for healthcare: Systematic review and architecture proposal." ACM Transactions on Intelligent Systems and Technology (TIST) 13, no. 4 (2022): 1-23.
Li, Q., Wen, Z., Wu, Z., Hu, S., Wang, N., Li, Y., ... & He, B. (2021). A survey on federated learning systems: vision, hype and reality for data privacy and protection. IEEE Transactions on Knowledge and Data Engineering. Sun, Peng, Xu Chen, Guocheng Liao, and Jianwei Huang. "A Profit-Maximizing Model Marketplace with Differentially Private Federated Learning." In IEEE INFOCOM 2022-IEEE Conference on Computer Communications, pp. 1439-1448. IEEE, 2022. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012), 1097–1105. Van de Ven, Gido M., Tinne Tuytelaars, and Andreas S. Tolias. "Three types of incremental learning." Nature Machine Intelligence (2022): 1-13. Van de Ven, Gido M., and Andreas S. Tolias. "Three scenarios for continual learning." arXiv preprint arXiv:1904.07734 (2019). Buzzega, Pietro, Matteo Boschini, Angelo Porrello, and Simone Calderara. "Rethinking experience replay: a bag of tricks for continual learning." In 2020 25th International Conference on Pattern Recognition (ICPR), pp. 2180-2187. IEEE, 2021. Kirkpatrick, James, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan et al. "Overcoming catastrophic forgetting in neural networks." Proceedings of the national academy of sciences 114, no. 13 (2017): 3521-3526. Li, Zhizhong, and Derek Hoiem. "Learning without forgetting." IEEE transactions on pattern analysis and machine intelligence 40, no. 12 (2017): 2935-2947. Rebuffi, Sylvestre-Alvise, Alexander Kolesnikov, Georg Sperl, and Christoph H. Lampert. "icarl: Incremental classifier and representation learning." In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 2001-2010. 2017. Castro, Francisco M., Manuel J. Marín-Jiménez, Nicolás Guil, Cordelia Schmid, and Karteek Alahari. "End-to-end incremental learning." In Proceedings of the European conference on computer vision (ECCV), pp. 233-248. 2018. Chen, Yueru, LeCun, Yann, Bernhard Boser, John S. Denker, Donnie Henderson, Richard E. Howard, Wayne Hubbard, and Lawrence D. Jackel. "Backpropagation applied to handwritten zip code recognition." Neural computation 1, no. 4 (1989): 541-551. LeCun, Yann, Léon Bottou, Yoshua Bengio, and Patrick Haffner. “Gradientbased learning applied to document recognition." Proceedings of the IEEE 86, no. 11 (1998): 2278-2324. O'Shea, Keiron, and Ryan Nash. "An introduction to convolutional neural networks." arXiv preprint arXiv:1511.08458 (2015). Howard, Andrew G., Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. "Mobilenets: Efficient convolutional neural networks for mobile vision applications." arXiv preprint arXiv:1704.04861 (2017) Sandler, Mark, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. "Mobilenetv2: Inverted residuals and linear bottlenecks." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4510-4520. 2018. Howard, Andrew, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang et al. "Searching for mobilenetv3." In Proceedings of the IEEE/CVF international conference on computer vision, pp. 1314-1324. 2019. Hu, Jie, Li Shen, and Gang Sun. "Squeeze-and-excitation networks." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7132-7141. 2018. Han, Kai, Yunhe Wang, Qi Tian, Jianyuan Guo, Chunjing Xu, and Chang Xu. "Ghostnet: More features from cheap operations." In Proceedings of the IEEE/ CVF conference on computer vision and pattern recognition, pp. 1580-1589. 2020. Tang, Yehui, Kai Han, Jianyuan Guo, Chang Xu, Chao Xu, and Yunhe Wang. "GhostNetV2: Enhance Cheap Operation with Long-Range Attention." arXiv preprint arXiv:2211.12905 (2022). Kuo, C-C. Jay, and Azad M. Madni. "Green learning: Introduction, examples and outlook." Journal of Visual Communication and Image Representation (2022): 103685. Kuo, C-C. Jay, Min Zhang, Siyang Li, Jiali Duan, and Yueru Chen. "Interpretable convolutional neural networks via feedforward design." Journal of Visual Communication and Image Representation 60 (2019): 346-359. Liu, Xiaofeng, Fangxu Xing, Hanna K. Gaggin, Weichung Wang, C-C. Jay Kuo, Georges El Fakhri, and Jonghye Woo. "Segmentation of cardiac structures via successive subspace learning with saab transform from cine mri." In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 3535-3538. IEEE, 2021. Otsu, Nobuyuki. "A threshold selection method from gray-level histograms." IEEE transactions on systems, man, and cybernetics 9, no. 1 (1979): 62-66. Canny, John. "A computational approach to edge detection." IEEE Transactions on pattern analysis and machine intelligence 6 (1986): 679-698 Long, Jonathan, Evan Shelhamer, and Trevor Darrell. "Fully convolutional networks for semantic segmentation." In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431-3440. 2015. Olaf Ronneberger, Philipp Fischer, and Thomas Brox, “U-net: Convolutional networks for biomedical image segmentation,” International Conference on Medical image computing and computer-assisted intervention (MICCAI), pp. 234– 241, 2015. He, Kaiming, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. "Mask r-cnn." In Proceedings of the IEEE international conference on computer vision, pp. 2961-2969. 2017. Chen, Liang-Chieh, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L. Yuille. "Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs." IEEE transactions on pattern analysis and machine intelligence 40, no. 4 (2017): 834-848. Chen, Tianqi, Tong He, Michael Benesty, Vadim Khotilovich, Yuan Tang, Hyunsu Cho, Kailong Chen, Rory Mitchell, Ignacio Cano, and Tianyi Zhou. "Xgboost: extreme gradient boosting." R package version 0.4-2 1, no. 4 (2015): 1-4. Chang CW, Lai F, Christian M, Chen YC, Hsu C, Chen YS, Chang DH, Roan TL, Yu YC. Deep Learning-Assisted Burn Wound Diagnosis: Diagnostic Model Development Study. JMIR Med Inform. 2021 Dec 2;9(12):e22798. doi: 10.2196/22798. PMID: 34860674; PMCID: PMC8686480. Jing, Junfeng, Zhen Wang, Matthias Rätsch, and Huanhuan Zhang. “MobileUnet: An efficient convolutional neural network for fabric defect detection." Textile Research Journal 92, no. 1-2 (2022): 30-42. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88009 | - |
dc.description.abstract | 在現代醫療體系中,主要醫院具有豐富的資源,而分院的資源相對較少。因此,主要醫院會負責訓練深度學習模型,而分院則將其收集的數據提供給主要醫院進行訓練。
本論文的研究目標是在此背景下,探討分院需要累積多少數據,再和主要醫院的數據一起進行訓練,期望在每間參與醫院的測試集上顯著提升模型性能。除了使用燒燙傷的數據集,我們也在交通工具的數據集上模擬了加入不同訓練資料量的情景。除此之外,考慮到主要醫院需要持續接收並訓練新數據,我們的研究目標也嘗試使用綠色學習的架構,運用多種輕量化的模型,旨在接近原始燒燙傷分割模型的結果,同時降低訓練模型時所需的資源和成本。 | zh_TW |
dc.description.abstract | The main hospital has abundant resources in the modern medical system, while the branch hospitals have relatively few resources. Usually, the main hospital will train the deep learning model, and the branches will provide the data it collects to the main hospital for training.
In this study, our goal is to analyze how much data the branch hospital needs to accumulate and train with the data of the main hospital in this context to significantly improve the model performance on the test dataset of each participating hospital. Besides the burn dataset, we simulated scenarios with varying training data volumes using the transportation dataset. Furthermore, considering that the main hospital needs to continuously receive and train new data, our research goal also attempts to utilize green learning frameworks and various lightweight models. The aim is to approximate the initial burns segmentation model results while reducing the resources and costs required during further model training. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-01T16:22:44Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2023-08-01T16:22:44Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | 口試委員會審定書... ...............................i
誌謝............................................iii 中文摘要.........................................iv ABSTRACT.........................................v CONTENTS........................................vi LIST OF FIGURES...............................viii LIST OF TABLES..................................ix Chapter 1 Introduction.....................1 Chapter 2 Related Works....................3 2.1 Incremental Learning.....................3 2.1.1 Task Incremental.........................3 2.1.2 Domain Incremental.......................4 2.1.3 Class Incremental........................5 2.2 Convolutional Neural Network.............5 2.3 Lightweight Architecture.................7 2.4 Green Learning..........................14 2.4.1 Unsupervised Representation Learning....14 2.4.2 Supervised Feature Learning.............16 2.4.3 Supervised Decision Learning............17 2.5 Segmentation............................17 2.5.1 Non-deep-learning-based Methods.........18 2.5.2 Deep-learning-based Methods.............19 2.6 Loss Function...........................20 Chapter 3 Research Methods................22 3.1 Data Processing and Augmentation........22 3.2 Data-Quantity Scenarios.................24 3.3 Green-Learning-based Segmentation.......25 3.4 Deep-Learning-based Segmentation........27 3.4.1 Network Architecture....................28 Chapter 4 Experiment Result...............31 4.1 Dataset.................................31 4.2 Evaluation Metrics......................31 4.3 Diverse Data Quantity Evaluations.......34 4.3.1 Homogeneous dataset.....................34 4.3.2 Heterogeneous dataset...................40 4.3.3 Ablation Study on Heterogeneous Data....44 4.4 Segmentation............................47 4.4.1 GL-based................................47 4.4.2 Limitations and Challenges..............49 4.4.3 DL-based Model Comparison...............52 Chapter 5 Conclusion and Future Work......55 5.1 Conclusion..............................55 5.2 Future Work.............................55 REFERENCE.......................................57 | - |
dc.language.iso | en | - |
dc.title | 實際情境下訓練數據對模型性能影響的量化分析及輕量級神經網絡的應用 | zh_TW |
dc.title | Quantitative Analysis of the Impact of Training Data on Model Performance in Real-World Scenarios and the Application of Lightweight Neural Networks | en |
dc.type | Thesis | - |
dc.date.schoolyear | 111-2 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 張哲瑋;傅楸善;顏廷聿;劉庭祿 | zh_TW |
dc.contributor.oralexamcommittee | Che-Wei Chang;Chiou-Shann Fuh;Ting-Yu Yan;Ting-Lu Liu | en |
dc.subject.keyword | 增量式學習,深度學習,綠色學習,燒燙傷傷口辨識,輕量化神經網路,語義分割,U-Net, | zh_TW |
dc.subject.keyword | incremental learning,deep learning,green learning,burn wound recognition,lightweight neural network,semantic segmentation,U-Net, | en |
dc.relation.page | 61 | - |
dc.identifier.doi | 10.6342/NTU202301015 | - |
dc.rights.note | 未授權 | - |
dc.date.accepted | 2023-07-06 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 資訊網路與多媒體研究所 | - |
顯示於系所單位: | 資訊網路與多媒體研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-111-2.pdf 目前未授權公開取用 | 2.9 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。