請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97413完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 簡韶逸 | zh_TW |
| dc.contributor.advisor | Shao-Yi Chien | en |
| dc.contributor.author | 曾郁瑄 | zh_TW |
| dc.contributor.author | Yu-Syuan Tseng | en |
| dc.date.accessioned | 2025-06-05T16:09:52Z | - |
| dc.date.available | 2025-06-06 | - |
| dc.date.copyright | 2025-06-05 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-05-23 | - |
| dc.identifier.citation | [1] AlittleQ, “Person re-identification,” https://ithelp.ithome.com.tw/m/articles/10241504, 2020, accessed: 2025-04-10. xi, 3
[2] M. Hirzer, C. Beleznai, P. M. Roth, and H. Bischof, “Person re-identification by descriptive and discriminative classification,” in Proceedings of the 17th Scandinavian Conference on Image Analysis, ser. SCIA’11. Berlin, Heidelberg: Springer-Verlag, 2011, p. 91–102. xi, 5 [3] C.-T. L. S.-Y. C. Yu-Syuan Tseng, Tzu-Chin Hsu, “Fedcapr:federated cameraaware unsupervised person re-identification with identity-distributed equalization for decentralized data clustering,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. PMLR, 2025. xi, 1, 12, 13, 25, 30, 35, 36, 38, 46, 47 [4] A. Li, J. Sun, B. Wang, L. Duan, S. Li, Y. Chen, and H. Li, “Lotteryfl: Empower edge intelligence with personalized and communication-efficient federated learning,” in 2021 IEEE/ACM Symposium on Edge Computing (SEC), 2021, pp. 68–79. xi, 13, 14, 18, 30, 45 [5] Q. Long, C. Anagnostopoulos, S. P. Parambath, and D. Bi, “Feddip: Federated learning with extreme dynamic pruning and incremental regularization,” in 2023 IEEE International Conference on Data Mining (ICDM). IEEE, 2023, pp. 1187–1192. xi, 14, 15, 45 [6] W. Zhuang, Y. Wen, and S. Zhang, “Joint optimization in edgecloud continuum for federated unsupervised person re-identification,” in Proceedings of the 29th ACM International Conference on Multimedia, ser. MM ’21. ACM, Oct. 2021, p. 433–441. [Online]. Available: http://dx.doi.org/10.1145/3474085.3475182 1, 24, 46 [7] J.Weng, K. Hu, T. Yao, J.Wang, and Z.Wang, “Robust knowledge adaptation for federated unsupervised person reid,” in 2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA). IEEE, 2022, pp. 1–8. 1, 24, 35, 36, 46 [8] Weng, Jianfeng and Hu, Kun and Yao, Tingting and Wang, Jingya and Wang, Zhiyong, “Federated unsupervised cluster-contrastive learning for person re-identification: A coarse-to-fine approach,” Comput. Vis. Image Underst., vol. 237, no. C, Dec. 2023. [Online]. Available: https://doi.org/10.1016/j.cviu.2023.103831 1, 12, 24, 46 [9] J. Liu, W. Zhuang, Y. Wen, J. Huang, and W. Lin, “Optimizing federated unsupervised person re-identification via camera-aware clustering,” in 2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP). IEEE, 2022, pp. 1–6. 1, 12, 24, 35, 36, 46 [10] H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” 2023. [Online]. Available: https://arxiv.org/abs/1602.05629 1 [11] W. Wen, C. Wu, Y. Wang, Y. Chen, and H. Li, “Learning structured sparsity in deep neural networks,” 2016. [Online]. Available: https://arxiv.org/abs/1608.03665 4 [12] S. Han, H. Mao, and W. J. Dally, “Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding,”2016. [Online]. Available: https://arxiv.org/abs/1510.00149 4 [13] Y. Zhao, M. Li, L. Lai, N. Suda, D. Civin, and V. Chandra, “Federated learning with non-iid data,” 2018. [Online]. Available: https://arxiv.org/abs/1806.00582 4, 6 [14] B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Artificial intelligence and statistics. PMLR, 2017, pp. 1273–1282. 6, 11, 24 [15] T. Li, A. K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, and V. Smith, “Federated optimization in heterogeneous networks,” 2020. [Online]. Available: https://arxiv.org/abs/1812.06127 6, 11 [16] M. Duan, D. Liu, X. Ji, R. Liu, L. Liang, X. Chen, and Y. Tan, “Fedgroup: Efficient federated learning via decomposed similarity-based clustering,” in 2021 IEEE Intl Conf on Parallel Distributed Processing with Applications, Big Data Cloud Computing, Sustainable Computing Communications, Social Computing Networking (ISPA/BDCloud/SocialCom/SustainCom), 2021, pp. 228–237. 6 [17] A. Fallah, A. Mokhtari, and A. Ozdaglar, “Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach,” in Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, and H. Lin, Eds., vol. 33. Curran Associates, Inc., 2020, pp. 3557–3568. [Online]. Available: https://proceedings.neurips.cc/paper files/paper/2020/file/24389bfe4fe2eba8bf9aa9203a44cdad-Paper.pdf 11 [18] C. T. Dinh, N. H. Tran, and T. D. Nguyen, “Personalized federated learning with moreau envelopes,” 2022. [Online]. Available: https://arxiv.org/abs/2006.08848 11 [19] T. Li, S. Hu, A. Beirami, and V. Smith, “Ditto: Fair and robust federated learning through personalization,” 2021. [Online]. Available: https://arxiv.org/abs/2012.04221 11 [20] Y. Huang, L. Chu, Z. Zhou, L. Wang, J. Liu, J. Pei, and Y. Zhang, “Personalized cross-silo federated learning on non-iid data,” 2021. [Online]. Available: https://arxiv.org/abs/2007.03797 11 [21] X.-C. Li, D.-C. Zhan, Y. Shao, B. Li, and S. Song, “Fedphp: Federated personalization withnbsp;inherited private models,” in Machine Learning and Knowledge Discovery in Databases. Research Track: European Conference, ECML PKDD 2021, Bilbao, Spain, September 13–17, 2021, Proceedings, Part I. Berlin, Heidelberg: Springer-Verlag, 2021, p. 587–602. [Online]. Available: https://doi.org/10.1007/978-3-030-86486-6 36 11 [22] M. Zhang, K. Sapra, S. Fidler, S. Yeung, and J. M. Alvarez, “Personalized federated learning with first order model optimization,” 2021. [Online]. Available: https://arxiv.org/abs/2012.08565 11 [23] J. Luo and S. Wu, “Adapt to adaptation: Learning personalization for cross-silo federated learning,” 2022. [Online]. Available: https://arxiv.org/abs/2110.08394 11 [24] S. Ioffe and C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift,” in Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37, ser. ICML’15. JMLR.org, 2015, p. 448–456. 12 [25] M. Wang, B. Lai, J. Huang, X. Gong, and X.-S. Hua, “Camera-aware proxies for unsupervised person re-identification,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 4, pp. 2764–2772, May 2021. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/16381 12, 21, 22 [26] W. Zhuang, X. Gan, Y. Wen, and S. Zhang, “Easyfl: A low-code federated learning platform for dummies,” IEEE Internet of Things Journal, 2022. 12, 40 [27] T. Li, A. K. Sahu, A. Talwalkar, and V. Smith, “Federated learning: Challenges, methods, and future directions,” IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 50–60, 2020. 12 [28] D. Alistarh, T. Hoefler, M. Johansson, S. Khirirat, N. Konstantinov, and C. Renggli, “The convergence of sparsified gradient methods,” in Proceedings of the 32nd International Conference on Neural Information Processing Systems, ser. NIPS’18. Red Hook, NY, USA: Curran Associates Inc., 2018, p. 5977–5987. 12 [29] Y. Cheng, D. Wang, P. Zhou, and T. Zhang, “A survey of model compression and acceleration for deep neural networks,” 2020. [Online]. Available: https://arxiv.org/abs/1710.09282 13 [30] Y. Jiang, S.Wang, V. Valls, B. J. Ko,W.-H. Lee, K. K. Leung, and L. Tassiulas, “Model pruning enables efficient federated learning on edge devices,” IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 12, pp. 10 374–10 386, 2023. 13 [31] S. Vahidian, M. Morafah, and B. Lin, “Personalized federated learning by structured and unstructured pruning under data heterogeneity,” 2021. [Online]. Available: https://arxiv.org/abs/2105.00562 13, 45 [32] W. Sun, F. Liu, and W. Xu, “Unlabeled samples generated by gan improve the person re-identification baseline,” in Proceedings of the 2019 5th International Conference on Computer and Technology Applications, ser. ICCTA ’19. New York, NY, USA: Association for Computing Machinery, 2019, p. 117–123. [Online]. Available: https://doi.org/10.1145/3323933.3324091 35, 37, 52, 54 [33] L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian, “Scalable person re-identification: A benchmark,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), December 2015. 35, 37, 52, 54 [34] T. Wang, S. Gong, X. Zhu, and S. Wang, “Person re-identification by video ranking,” in Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV 13. Springer, 2014, pp. 688–703. 35, 37, 52, 54 [35] W. Li, R. Zhao, T. Xiao, and X. Wang, “Deepreid: Deep filter pairing neural network for person re-identification,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 152–159. 35, 37, 52, 54 [36] M. Hirzer, C. Beleznai, P. M. Roth, and H. Bischof, “Person re-identification by descriptive and discriminative classification,” in Image Analysis: 17th Scandinavian Conference, SCIA 2011, Ystad, Sweden, May 2011. Proceedings 17. Springer, 2011, pp. 91–102. 35, 37, 52, 54 [37] D. Gray and H. Tao, “Viewpoint invariant pedestrian recognition with an ensemble of localized features,” in Computer Vision–ECCV 2008: 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008, Proceedings, Part I 10. Springer, 2008, pp. 262–275. 35, 37, 52, 54 [38] W. Li, R. Zhao, and X. Wang, “Human reidentification with transferred metric learning,” in Asian conference on computer vision. Springer, 2012, pp. 31–44. 35, 37, 52, 54 [39] D. Baltieri, R. Vezzani, and R. Cucchiara, “3dpes: 3d people dataset for surveillance and forensics,” in Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding, 2011, pp. 59–64. 36, 37, 52, 54 [40] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2015. [Online]. Available: https://arxiv.org/abs/1512.03385 36 [41] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 248–255. 36 [42] A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. K¨opf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, PyTorch: an imperative style, high-performance deep learning library. Red Hook, NY, USA: Curran Associates Inc., 2019. 40 | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97413 | - |
| dc.description.abstract | 隨著智慧城市快速發展，行人重識別（Person Re-Identification, ReID）技術於公共安全與智慧監控領域的重要性日益凸顯。該技術的核心目標是從分散部署的異質攝影機網絡中，精準檢索並匹配同一行人的影像。
然而，實際應用面臨三大關鍵挑戰：首先，監控資料的敏感性所引發隱私問題，而多數研究透過聯邦式學習架構，將敏感性資料留在本地端進行分散式訓練，以避免原始數據的洩漏。然而，此方法亦衍生兩大技術瓶頸——其一為統計異質性（Statistical Heterogeneity）即跨場域數據分布的非獨立同分布（Non-IID）特性導致模型偏差；其二是傳輸延遲問題，因聯邦式學習反覆於邊緣與中心間交換模型所需的龐大通信負擔，而造成的顯著延遲問題。 為此，我們提出 FedKLPR——基於聯邦式學習架構所設計的輕量化行人重識別 (re-ID) 任務。該方法通過剪枝技術在確保模型準確率下降低於1% 的同時，分別在ResNet-50及ResNet-34的模型架構上降低35.01% 及30.58% 的傳輸負擔，以提升學習效率。總結來說，我們提出的FedKLPR在不犧牲隱私與準確率的前提下，顯著地降低通訊成本，同時增強模型的個性化能力與實用性，為基於聯邦式學習的行人重識別任務提供了一條可行的輕量化發展路徑。 | zh_TW |
| dc.description.abstract | As smart cities continue to evolve, the role of person re-identification (re-ID) has grown crucial in enabling effective public surveillance and enhancing urban safety measures. The fundamental challenge in person re-identification lies in developing robust cross-camera matching capabilities across diverse surveillance systems to reliably associate images of identical subjects.
However, deployment on real-world faces three major challenges. First, the sensitive surveillance data raises significant privacy concerns. To address this, many studies adopt a federated learning framework, which enables decentralized training by keeping data on local devices, thereby mitigating privacy risks. Nevertheless, this approach introduces two critical technical bottlenecks. First, statistical heterogeneity, where the non-independent and identically distributed (non-IID) data across different domains leads to biased model performance. Second, communication latency, caused by the substantial transmission overhead incurred by frequent model exchanges between edge devices and the central server. To tackle these issues, we proposed FedKLPR, a lightweight person re-ID framework built upon the federated learning framework. By incorporating pruning techniques, FedKLPR reduces the communication cost by 35.01% on ResNet-50 and 30.58% on ResNet-34, while ensuring that the model accuracy drops by less than 1%. In summary, FedKLPR achieves a significant reduction in communication cost without sacrificing privacy or accuracy, and simultaneously enhances model personalization and practical applicability, offering a viable and efficient solution for federated person re-identification tasks. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-06-05T16:09:52Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-06-05T16:09:52Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Master’s Thesis Acceptance Certificate i
Acknowledgement iii Chinese Abstract v Abstract vii Contents ix List of Figures xi List of Tables xiii 1 Introduction 1 1.1 Unsupervised Federated Person Re-ID . . . . . . . . . . . . . . . 1 1.2 Introduction of Sparsity . . . . . . . . . . . . . . . . . . . . . . . 2 1.3 Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.4 Contribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 1.5 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . 9 2 Related Work 11 2.1 Related work . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.1.1 Federated Learning . . . . . . . . . . . . . . . . . . . . . 11 2.1.2 Unsupervised Federated Person Re-ID . . . . . . . . . . 12 2.1.3 Network Pruning . . . . . . . . . . . . . . . . . . . . . . 12 3 Proposed Method 17 3.1 Architecture of Personalized Federated Learning in FedKLPR . . 18 3.2 Overview of FedKLPR . . . . . . . . . . . . . . . . . . . . . . . 19 3.2.1 Proxy Creation and the Memory Bank . . . . . . . . . . . 21 3.3 KL-Divergence Regularization loss (KLL) . . . . . . . . . . . . . 22 3.4 KL-Divergence Weight(KLW) . . . . . . . . . . . . . . . . . . . 24 3.5 Pruning Ratio Weight(PRW) . . . . . . . . . . . . . . . . . . . . 27 3.6 Sparse Activation Skipping(SAS) . . . . . . . . . . . . . . . . . 30 3.7 Cross-Round Recovery(CRR) . . . . . . . . . . . . . . . . . . . 32 4 Experiments 35 4.1 Experiments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 4.2 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . 35 4.2.1 Evaluation Metrics. . . . . . . . . . . . . . . . . . . . . . 38 4.3 Training and Implementation Details . . . . . . . . . . . . . . . . 40 4.4 Performance Evaluation . . . . . . . . . . . . . . . . . . . . . . . 45 4.4.1 Performance Evaluation of non-Pruning . . . . . . . . . . 45 4.4.2 Performance Evaluation of Pruning . . . . . . . . . . . . 48 4.5 Ablation Study . . . . . . . . . . . . . . . . . . . . . . . . . . . 59 5 Conclusion 63 Reference 65 | - |
| dc.language.iso | en | - |
| dc.subject | 資料隱私 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 模型剪枝 | zh_TW |
| dc.subject | 行人重識別 | zh_TW |
| dc.subject | 聯邦式學習 | zh_TW |
| dc.subject | Deep learning | en |
| dc.subject | Federated Learning | en |
| dc.subject | Person Re-identification | en |
| dc.subject | Model Pruning | en |
| dc.subject | Data Privacy | en |
| dc.title | 基於自適應剪枝的聯邦行人重識別個性化框架 | zh_TW |
| dc.title | FedKLPR: Personalized Federated Learning for Person Re-Identification with Adaptive Pruning | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 陳祝嵩;曹昱;陳駿丞 | zh_TW |
| dc.contributor.oralexamcommittee | Chu-Song Chen;Yu Tsao;Jun-Cheng Chen | en |
| dc.subject.keyword | 聯邦式學習,行人重識別,模型剪枝,資料隱私,深度學習, | zh_TW |
| dc.subject.keyword | Federated Learning,Person Re-identification,Model Pruning,Data Privacy,Deep learning, | en |
| dc.relation.page | 71 | - |
| dc.identifier.doi | 10.6342/NTU202500961 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2025-05-23 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 電子工程學研究所 | - |
| dc.date.embargo-lift | 2027-06-30 | - |
| 顯示於系所單位： | 電子工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf 未授權公開取用 | 43.75 MB | Adobe PDF | 檢視/開啟 |
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。