請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97753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 | 徐子晴 | zh_TW |
| dc.contributor.author | Tzu-Ching Hsu | en |
| dc.date.accessioned | 2025-07-16T16:09:29Z | - |
| dc.date.available | 2025-07-17 | - |
| dc.date.copyright | 2025-07-16 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-05-29 | - |
| dc.identifier.citation | [1] M. Wang, B. Lai, J. Huang, X. Gong, and X.-S. Hua, “Camera-aware proxies for unsupervised person re-identification,” in Proceedings of The Association for the Advancement of Artificial Intelligence (AAAI), 2021, pp. 2764–27 772. xi, 10, 11, 13, 22, 23, 24, 25
[2] J. Weng, K. Hu, T. Yao, J. Wang, and Z. Wang, “Federated unsupervised cluster-contrastive learning for person re-identification: A coarse-to-fine approach,” Computer Vision and Image Understanding (CVIU), 2023. xi, 12, 13, 14, 31, 42, 45, 48 [3] J. Liu, W. Zhuang, Y. Wen, J. Huang, and W. Lin, “Optimizing federated unsupervised person re-identification via camera-aware clustering,” in Proceedings of IEEE International Workshop on Multimedia Signal Processing (MMSP), 2022, pp. 1–6. xi, 13, 15, 31, 42, 45, 47, 48 [4] S. We, Y. Bai, C. Wang, and L. Duan, “Person retrieval with conv-transformer,” in Proceedings of IEEE International Conference on Multimedia and Expo (ICME), 2021, pp. 1–6. 1 [5] V. Sovrasov and D. Sidnev, “Building computationally efficient and well generalizing person re-identification models with metric learning,” in Proceedings of International Conference on Pattern Recognition (ICPR), 2021, pp. 639–646. 1 [6] W. Zhuang, Y. Wen, W. Zhang, X. Gan, D. Yin, D. Zhou, S. Zhang, and S. Yi, “Performance optimization of federated person re-identification via benchmark analysis,”in Proceedings of 28th ACM Int. Conf. Multimedia (MM’20), 2020, pp. 955–963. 1, 3, 11 [7] G. Research. (2017) Federated learning: Collaborative machine learning without centralized training data. [Online]. Available: https://research.google/blog/federated-learning-collaborative-machine-learning-without-centralized-training-data/1 [8] AlittleQ. (2020) Person re-identification. [Online]. Available: https://ithelp.ithome.com.tw/m/articles/10241504 2 [9] J. Weng, K. Hu, T. Yao, J. Wang, and Z. Wang, “Robust knowledge adaptation for federated unsupervised person reid,” in International Conference on Digital Image Computing: Techniques and Applications (DICTA). IEEE, 2022, pp. 1–8. 3, 12, 13, 31, 45, 48 [10] W. Zhuand, Y. Wen, and S. Zhang, “Joint optimization in edge-cloud continuum for federated unsupervised person re-identification,” in 29th ACM Int. Conf. Multimedia (MM’21), 2021, p. 433–441. 3, 11, 31, 40, 44, 45, 48 [11] W. Li, R. Zhao, and X. Wang, “Human reidentification with transferred metric learning,” in Proceedings of Asian Conference on Computer Vision (ACCV), 2012, p. 31–44. 4, 35, 37, 39 [12] M. Hirzer, P. Roth, C. Beleznai, and H. Bischof, “Person re-identification by descriptive and discriminative classification,” in Proceedings of the Scandinavian Conference on Image Analysis (SCIA), 2011, p. 91–102. 4, 35, 37, 39 [13] H. 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, 2017, pp. 1273–1282. 6, 11, 13, 31 [14] L. Wei, S. Zhang, W. Gao, and Q. Tian, “Person transfer gan to bridge domain gap for person re-identification,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 79–88. 9 [15] Y. Chen, X. Zhu, and S. Gong, “Instance-guided context rendering for cross-domain person re-identification,” in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019, pp. 232–242. 9 [16] Y. Ge, D. Chen, and H. Li, “Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification,” in Proceedings of International Conference on Learning Representations (ICLR), 2020. 9, 46 [17] J. Lv, W. Chen, Q. Li, and C. Yang, “Unsupervised cross-dataset person re-identification by transfer learning of spatial-temporal patterns,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 7948–7956. 9 [18] J. Liu, Z. J. Zha, D. Chen, R. Hong, and M. Wang, “Adaptive transfer network for cross-domain person re-identification,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 7202–7211. 9 [19] T. Isobe, D. Li, L. Tian, W. Chen, Y. Shan, and S. Wang, “Towards discriminative representation learning for unsupervised person re-identification,” in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2021, pp. 8526–8536. 10 [20] S. Xuan and S. Zhang, “Intra-inter camera similarity for unsupervised person re-identification,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021. 10, 46 [21] M. Li, X. Zhu, and S. Gong, “Unsupervised person re-identification by deep learning tracklet association,” in Proceedings of European Conference on Computer Vision (ECCV), 2018, pp. 737–753. 10 [22] Y. Chen, X. Zhu, and S. Gong, “Deep association learning for unsupervised video person re-identification,” arXiv preprint arXiv:1808.07301, 2018. 10 [23] M. Ye, A. J. Ma, L. Zheng, J. Li, and P. C. Yuen, “Dynamic label graph matching for unsupervised video re-identification,” in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2017, pp. 5142–5150. 10 [24] J. Wu, Y. Yang, H. Liu, S. Liao, Z. Lei, and S. Z. Li, “Unsupervised graph association for person re-identification,” in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2019, pp. 8321–8330. 10 [25] M. Ester, H.-P. Kriegal, J. Sander, and X. Xu, “A density-based algorithm for discovering clusters in large spatial databases with noise,” in Proceedings of The Association for the Advancement of Artificial Intelligence (AAAI), 1996, pp. 226–231. 10, 21, 22, 33 [26] Y. Lin, X. Dong, L. Zheng, Y. Yan, and Y. Yang, “A bottom-up clustering approach to unsupervised person re-identification,” in Proceedings of The Association for the Advancement of Artificial Intelligence (AAAI), 2019, pp.8738–8745. 10 [27] H.-X. Yu, W.-S. Zheng, A. Wu, X. Guo, S. Gong, and J.-H. Lai, “Unsupervised person re-identification by soft multilabel learning,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 2148–2157. 10 [28] Z. Wu, Y. Xiong, S. X. Yu, and D. Lin, “Unsupervised feature learning via non-parametric instance discrimination,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 3733–3742. 10 [29] T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, “A simple framework for contrastive learning of visual representations,” in International conference on machine learning (ICML). PMLR, 2020, pp. 1597–1607. 10 [30] K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick, “Momentum contrast for unsupervised visual representation learning,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 9729–9738. 10 [31] T. Li, A. K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, and V. Smith, “Federated optimization in heterogeneous networks,” Proceedings of Machine learning and systems, vol. 2, pp. 429–450, 2020. 11 [32] G. Wu and S. Gong, “Decentralised learning from independent multi-domain labels for person re-identification,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 4, 2021, pp. 2898–2906. 11 [33] S. Sun, G. Wu, and S. Gong, “Decentralised person re-identification with selective knowledge aggregation,” arXiv preprint arXiv:2110.11384, 2021. 11 [34] A. Fallah, A. Mokhtari, and A. Ozdaglar, “Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach,” Advances in neural information processing systems, vol. 33, pp. 3557–3568, 2020. 12 [35] C. T Dinh, N. Tran, and J. Nguyen, “Personalized federated learning with moreau envelopes,” Advances in neural information processing systems, vol. 33, pp. 21 394–21 405, 2020. 12 [36] T. Li, S. Hu, A. Beirami, and V. Smith, “Ditto: Fair and robust federated learning through personalization,” in International conference on machine learning. PMLR, 2021, pp. 6357–6368. 12 [37] Y. Huang, L. Chu, Z. Zhou, L. Wang, J. Liu, J. Pei, and Y. Zhang, “Personalized cross-silo federated learning on non-iid data,” in Proceedings of the AAAI conference on artificial intelligence, vol. 35, no. 9, 2021, pp. 7865–7873. 12 [38] X.-C. Li, D.-C. Zhan, Y. Shao, B. Li, and S. Song, “Fedphp: Federated personalization with inherited private models,” in Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 2021, pp. 587–602. 12 [39] M. Zhang, K. Sapra, S. Fidler, S. Yeung, and J. M. Alvarez, “Personalized federated learning with first order model optimization,” arXiv preprint arXiv:2012.08565, 2020. 12 [40] J. Luo and S. Wu, “Adapt to adaptation: Learning personalization for cross-silo federated learning,” in Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), vol. 2022. NIH Public Access, 2022, p. 2166. 12 [41] W. Zhuang, X. Gan, Y. Wen, and S. Zhang, “Easyfl: A low-code federated learning platform for dummies,” pp. 13 740–13 754, 2022. 13, 41 [42] H. Yu, W. Zheng, A. Yu, X. Guo, S. Gong, and J. Lai, “Unsupervised person re-identification by soft multilabel learning,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 2143–2152. 20 [43] Z. Wu, Y. Xiong, S. X. Yu, and D. Lin, “Unsupervised feature learning via non-parametric instance discrimination,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 3733–3742. 22 [44] Z. Zhong, L. Zheng, Z. Luo, S. Li, and Y. Yang, “Invariance matters: Exempla memory for domain adaptive person re-identification,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 598–607. 22 [45] T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, “A simple framework for contrastive learning of visual representationsg,” 2020, pp. 1597–1607. 22 [46] K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick, “Momentum contrast for unsupervised visual representation learning,” in arXiv, 2019. 22 [47] Z. Zhong, L. Zheng, D. Cao, and S. Li, “Re-ranking person re-identification with k-reciprocal encoding,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1318–1327. 33 [48] Z. Zheng, L. Zhen, and Y. Yang, “Unlabeled samples generated by gan improve the person re-identification baseline in vitro.” in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2017. 33, 35, 37, 39 [49] L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian, “Scalable person re-identification: A benchmark,” in Proceedings of IEEE International Conference on Computer Vision (ICCV), 2015, p. 1116–1124. 33, 35, 37, 39, 40, 41 [50] T. Wang, S. Gong, X. Zhu, and S. Wang, “Person re-identification by video ranking,” in Proceedings of European Conference on Computer Vision (ECCV), 2014, p. 688–703. 34, 35, 37, 39 [51] W. Li, R. Zhao, T. Xiao, and X. Wang, “Deepreid: Deep filter pairing neural network for person re-identification,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. 35, 37, 39 [52] D. Baltieri, R. Vezzani, and R. Cucchiara, “3dpes: 3d people dataset for surveillance and forensics,” in Joint ACM Workshop on Human Gesture and Behavior Understanding, 2011, p. 59–64. 35, 37, 39 [53] W. Zhuang, Y. Wen, X. Zhang, X. Gan, D. Yin, D. Zhou, S. Zhang, and S. Yi, “Performance optimization of federated person re-identification via benchmark analysis,” in Proceedings of the 28th ACM International Conference on Multimedia, 2022, pp. 955–963. 37 [54] D. Gray and H. Tao, “Viewpoint invariant pedestrian recognition with an ensemble of localized features,” in Proceedings of European Conference on Computer Vision (ECCV), 2008, p. 262–275. 37, 39 [55] A. Paszke, S. Gross, F. Massa, A. Lerer, J. Drabury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, 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,” in Proceedings of Neural Information Processing Systems (NIPS), 2019, pp. 8026–8037. 41 [56] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. 41 [57] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009, pp. 248–255. 41 [58] F. Zhao, S. Liao, G.-S. Xie, J. Zhao, K. Zhang, and L. Shao, “Unsupervised domain adaptation with noise resistible mutual-training for person re-identification.” in Proceedings of European Conference on Computer Vision (ECCV), 2021, pp. 4420–4428. 46 [59] J. Li and S. Zhang, “Joint visual and temporal consistency for unsupervised domain adaptive person re-identification,” in Proceedings of European Conference on Computer Vision (ECCV), 2020. 46 [60] D. Wang and S. Zhang, “Unsupervised person re-identification via multi-label classification.” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020. 46 | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97753 | - |
| dc.description.abstract | 隨著智慧城市的快速發展，行人重識別（pedestrian re-identification）已成為監控影像中個體追蹤的重要技術。然而，這些方法需要大量已標註的資料，而標註過程耗時且費工，使其難以廣泛應用於實務場域。因此，本研究採用無監督學習方法，以消除對標註資料的需求，提升模型於真實場景下的適用性。
此外，監控影像中涉及個人面貌與特徵等敏感資訊，使得集中式訓練模式在隱私保護上日益受到挑戰。為此，本研究設計一個具個別化能力的聯邦學習架構，使多個資料保留於本地的客戶端可在無需共享原始資料的前提下協同訓練模型，有效平衡隱私保障與辨識性能。本研究所提出之整合框架結合無監督學習與聯邦學習於行人重識別任務中。於無監督學習部分，導入一種考慮攝影機資訊的對比式損失函數，以提升模型跨視角區分身份的能力；於聯邦學習部分，針對傳統 FedAvg 方法中常見的資訊不平衡問題，設計一個改良的參數聚合策略。同時，我們亦提出一項前處理技術，以降低無監督學習中的聚類雜訊並提升各客戶端對聚合模型訓練的貢獻。 本方法於八組公開基準資料集上進行評估，實驗結果顯示其具備先進的準確率與隱私保護效能，驗證了所提方法於智慧監控系統中之應用潛力，並為未來智慧城市中的安全、可擴展與智慧化監控系統之發展提供重要貢獻。 | zh_TW |
| dc.description.abstract | With the rise of smart cities, pedestrian re-identification (re-ID) has become crucial for tracking individuals across surveillance footage. However, its reliance on large labeled datasets limits practicality due to the high cost of manual annotation. To address this, we adopt pure unsupervised learning, which eliminates the need for labeled data and enhances real-world applicability.
Meanwhile, privacy concerns over sharing sensitive visual data make centralized training problematic. We propose a personalized federated learning (pFL) framework that enables decentralized clients to collaboratively train a model with out sharing raw data, preserving privacy while maintaining strong performance. Our framework combines unsupervised and federated learning for pedestrian re-ID. We introduce a contrastive loss leveraging camera-specific information and propose a refined aggregation strategy to address imbalances in traditional FedAvg. Additionally, a novel preprocessing method reduces clustering noise and improves each client’s contribution. Our method is evaluated on eight benchmark datasets, demonstrating state-of-the-art performance and validating its effectiveness in both preserving privacy and achieving high accuracy. By addressing the dual challenges of unsupervised learning and federated learning, this research significantly advances the development of secure, scalable, and intelligent surveillance systems for future smart cities. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-07-16T16:09:29Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-07-16T16:09:29Z (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 Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.3 Contribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2 Related Works 9 2.1 Unsupervised Person Re-ID . . . . . . . . . . . . . . . . . . . . 9 2.2 Federated Learning . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.3 Federated Unsupervised Person Re-ID . . . . . . . . . . . . . . . 12 3 Proposed Method 17 3.1 Overall Architecture . . . . . . . . . . . . . . . . . . . . . . . . 17 3.2 Camera-Aware Contrastive Learning . . . . . . . . . . . . . . . . 20 3.2.1 Proxy Creation and the Memory Bank . . . . . . . . . . . 20 3.2.2 Contrastive Learning with Proxies . . . . . . . . . . . . . 22 3.3 Regularization and Aggregation in Federated Learning . . . . . . 29 3.3.1 Regularization Loss . . . . . . . . . . . . . . . . . . . . 30 3.3.2 Aggregation Strategy Based on Cosine Distance Similarity 31 3.4 Identity-Distributed Equalization . . . . . . . . . . . . . . . . . . 33 4 Experimental Evaluation 37 4.1 Datasets and Evaluation Metrics . . . . . . . . . . . . . . . . . . 37 4.2 Implement Details . . . . . . . . . . . . . . . . . . . . . . . . . . 41 4.3 Performance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 4.3.1 Comparisons with the State-of-the-Arts . . . . . . . . . . 42 4.3.2 Ablation Study . . . . . . . . . . . . . . . . . . . . . . . 49 5 Conclusion 55 Reference 57 | - |
| dc.language.iso | en | - |
| dc.subject | 無監督學習 | zh_TW |
| dc.subject | 聯邦學習 | zh_TW |
| dc.subject | 行人重識別 | zh_TW |
| dc.subject | 對比學習 | zh_TW |
| dc.subject | Contrastive Learning | en |
| dc.subject | Person Re-ID | en |
| dc.subject | Federated Learning | en |
| dc.subject | Unsupervised Learning | en |
| dc.title | 具有相機感知能力之聯邦無監督行人重識別--均衡身份分布提升去中心化數據聚類效果 | zh_TW |
| dc.title | Federated Camera-Aware Unsupervised Person Re-Identification with Equalizing Identity Distribution for Decentralized Data Clustering | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 王鈺強;陳祝嵩;曹昱;陳駿丞 | zh_TW |
| dc.contributor.oralexamcommittee | Yu-Chiang Wang;Chu-Song Chen;Yu Tsao;Jun-Cheng Chen | en |
| dc.subject.keyword | 行人重識別,聯邦學習,無監督學習,對比學習, | zh_TW |
| dc.subject.keyword | Person Re-ID,Federated Learning,Unsupervised Learning,Contrastive Learning, | en |
| dc.relation.page | 65 | - |
| dc.identifier.doi | 10.6342/NTU202500990 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2025-05-29 | - |
| 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 | 2030-05-26 | - |
| 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 | 4.29 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。