請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/83950完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林守德(Shou-De Lin) | |
| dc.contributor.author | Cayon Liow Keei Yann | en |
| dc.contributor.author | 廖其忻 | zh_TW |
| dc.date.accessioned | 2023-03-19T21:24:48Z | - |
| dc.date.copyright | 2022-07-05 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-06-29 | |
| dc.identifier.citation | 1. MICE: Multivariate Imputation by Chained Equations in R. van Buuren, Stef and Groothuis-Oudshoorn, Karin. s.l. : Journal of Statistical Software, 2011, Vol. 45. 2. GAIN: Missing Data Imputation using Generative Adversarial Nets. Yoon, Jinsung and Jordon, James and van der Schaar, Mihaela. [ed.] Jennifer and Krause, Andreas Dy. s.l. : Proceedings of the 35th International Conference on Machine Learning, PMLR, 10--15 Jul 2018, pp. 5689--5698. 3. Handling Missing Data with Graph Representation Learning. Leskovec, Jiaxuan You and Xiaobai Ma and Daisy Yi Ding and Mykel Kochenderfer and Jure. s.l. : arXiv, 2020. 4. Distilling the knowledge in a neural network. Hinton, Geoffrey and Vinyals, Oriol and Dean, Jeff. s.l. : arXiv preprint arXiv:1503.02531, 2015. 5. Model compression. Bucilu?, Cristian and Caruana, Rich and Niculescu-Mizil, Alexandru. s.l. : Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, 2006. pp. 535--541. 6. Learning to Predict with Unavailable Features: an End-to-End Approach via Knowledge Transferring. Chun-Chen Lin, Li-Wei Chang, Chun-Pai Yang, and Shou-De Lin. s.l. : 17th International Conference on Machine Learning and Data Mining, ibai Publishing, 2021. 7. Deep metric learning using Triplet network. Ailon, Elad Hoffer and Nir. s.l. : arXiv, eprint: 1412.6622, 2018. 8. Signature Verification using a 'Siamese' Time Delay Neural Network. Bromley, Jane and Guyon, Isabelle and LeCun, Yann and S\'{a}ckinger, Eduard and Shah, Roopak. [ed.] J. Cowan and G. Tesauro and J. Alspector. s.l. : Advances in Neural Information Processing Systems, Morgan-Kaufmann, 1994. Vol. 6. 9. Siamese Neural Networks for One-shot Image Recognition. Koch, Gregory and Zemel, Richard and Salakhutdinov, Ruslan. 2015. 10. Fully-Convolutional Siamese Networks for Object Tracking. Torr, Luca Bertinetto and Jack Valmadre and Jo?o F. Henriques and Andrea Vedaldi and Philip H. S. s.l. : arXiv, eprint: 1606.09549, 2016. 11. Generalized Contrastive Optimization of Siamese Networks for Place Recognition. Leyva-Vallina, Mar{\'\i}a and Strisciuglio, Nicola and Petkov, Nicolai. s.l. : arXiv preprint arXiv:2103.06638, 2021. 12. Triplet Loss in Siamese Network for Object Tracking. Dong, Xingping and Shen, Jianbing. s.l. : Proceedings of the European Conference on Computer Vision (ECCV), 2018. 13. Rethinking triplet loss for domain adaptation. Deng, Weijian and Zheng, Liang and Sun, Yifan and Jiao, Jianbin. s.l. : IEEE Transactions on Circuits and Systems for Video Technology, 2020, Vol. 31, pp. 29--37. 14. Hierarchical Clustering-guided re-ID with Triplet loss. Zeng, Kaiwei. s.l. : CoRR, 2019, Vol. abs/1910.12278. 15. TS-NET: Combining modality specific and common features for multimodal patch matching. En, Sovann and Lechervy, Alexis and Jurie, Fr{\'e}d{\'e}ric. s.l. : 2018 25th IEEE International Conference on Image Processing (ICIP, 2018. pp. 3024--3028. 16. Unsupervised deep triplet hashing with pseudo triplets for scalable image retrieval. Gu, Yifan and Zhang, Haofeng and Zhang, Zheng and Ye, Qiaolin. s.l. : Multimedia Tools and Applications, Springer, 2020, Vol. 79. 17. Deep learning for SAR-optical image matching. Hughes, Lloyd Haydn and Merkle, Nina and B{\'u}rgmann, Tatjana and Auer, Stefan and Schmitt, Michael. s.l. : IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, 2019. pp. 4877--4880. 18. Partly uncoupled siamese model for change detection from heterogeneous remote sensing imagery. Touati, R and Mignotte, M and Dahmane, M. s.l. : Journal of Remote sensing and GIS, 2020, Vol. 9. 19. Wildcat: In-the-wild color-and-thermal patch comparison with deep residual pseudo-siamese networks. Treible, Wayne and Saponaro, Philip and Kambhamettu, Chandra. s.l. : 2019 IEEE International Conference on Image Processing (ICIP), 2019. pp. 1307--1311. 20. Pseudo Siamese Network for Few-shot Intent Generation}. Xia, Congying and Xiong, Caiming and Yu, Philip. s.l. : arXiv preprint arXiv:2105.00896, 2021. 21. Learning to Compare Image Patches via Convolutional Neural Networks. Zagoruyko, Sergey and Komodakis, Nikos. s.l. : Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. 22. Mask-guided Image Classification with Siamese Networks. Alqasir, Hiba and Muselet, Damien and Ducottet, Christophe. s.l. : International Conference on Computer Vision Theory and Applications, 2020. 23. COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching. Gao, Junyi and Xiao, Cao and Glass, Lucas M and Sun, Jimeng. s.l. : Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020. pp. 803--812. 24. Identifying corresponding patches in SAR and optical images with a pseudo-siamese CNN. Hughes, Lloyd H and Schmitt, Michael and Mou, Lichao and Wang, Yuanyuan and Zhu, Xiao Xiang. s.l. : IEEE Geoscience and Remote Sensing Letters, 2018, Vol. 15, pp. 784--788. 25. A CNN for the identification of corresponding patches in SAR and optical imagery of urban scenes. Mou, Lichao and Schmitt, Michael and Wang, Yuanyuan and Zhu, Xiao Xiang. s.l. : 2017 Joint Urban Remote Sensing Event (JURSE), 2017. pp. 1--4. 26. The Distributed Representation of Knowledge Graphs Based on Pseudo-Siamese Network. Wei, Zhuo and Zhang, Ye and Wang, Fan and Liu, Shuai. s.l. : IOP Conference Series: Earth and Environmental Science,, 2020. Vol. 440, p. 022012. 27. UCI Machine Learning Repository. [Online] University of California, Irvine, School of Information and Computer Sciences, 2017. http://archive.ics.uci.edu/ml. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/83950 | - |
| dc.description.abstract | 一種根據特徵子集合缺失的資料集應用場景被重新定義及命名為子集合缺失資料集。這種重新制定及定義有助於之後的場景應用以及簡化許多領域都會遇到的因資料集部分缺失的模型問題。此研究利用偽三元組神經元網絡之調用正反配對例子的特性來應對子集合缺失資料集的問題。此研究也涉及了一套資料前處理流程用於處理資料集以便用於模型之輸入。此研究對於多種資料集設定了多種不同比例的子集合缺失用於鑒定所設計模型的分類效能 | zh_TW |
| dc.description.abstract | The data scenario in which the absence of its value depends on the feature subset of the value is defined and formulated as Subset-incomplete data scenario. The formulation of the data scenario contributed to the future application of multiple field problems. Pseudo-triplet networks with positive and negative pairing and their corresponding data flow are proposed to tackle the subset-incomplete data scenario. Data preprocessing pipeline is designed to process subset-incomplete data into model-accepted data with positive and negative pairing. Experiments with various data feature settings for evaluation are observed to support the efficacy of the pseudo-triplet network. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T21:24:48Z (GMT). No. of bitstreams: 1 U0001-2706202213315600.pdf: 1090875 bytes, checksum: 6b9bd3ce2c01bd3eec81091e0594d9a8 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | Acknowledgments I 摘要 II Abstract III List of Figures V List of Tables VI Introduction 1 Related Work 4 Ignore and drop the feature 4 Data Imputation 5 Knowledge Distillation 6 Triplet Network 7 Methodology 9 Experiment 13 Conclusion 23 References 24 | |
| dc.language.iso | en | |
| dc.subject | 偽三元組網絡 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 三元組網絡 | zh_TW |
| dc.subject | 不完整資料集 | zh_TW |
| dc.subject | Pseudo Triplet Network | en |
| dc.subject | Deep Learning | en |
| dc.subject | Incomplete data | en |
| dc.subject | Machine Learning | en |
| dc.subject | Triplet Network | en |
| dc.title | 利用三元組網絡處理不完整資料集之應用 | zh_TW |
| dc.title | Triplet Network for Incomplete Data Classification | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 李政德(Cheng-Te Li),陳尚澤(Shang-Tse Chen) | |
| dc.subject.keyword | 深度學習,機器學習,三元組網絡,不完整資料集,偽三元組網絡, | zh_TW |
| dc.subject.keyword | Deep Learning,Machine Learning,Triplet Network,Pseudo Triplet Network,Incomplete data, | en |
| dc.relation.page | 28 | |
| dc.identifier.doi | 10.6342/NTU202201139 | |
| dc.rights.note | 未授權 | |
| dc.date.accepted | 2022-06-29 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2706202213315600.pdf 未授權公開取用 | 1.07 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。