請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74045
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 莊永裕(Yung-Yu Chuang) | |
dc.contributor.author | Chiao-An Yang | en |
dc.contributor.author | 楊喬諳 | zh_TW |
dc.date.accessioned | 2021-06-17T08:17:53Z | - |
dc.date.available | 2019-08-20 | |
dc.date.copyright | 2019-08-20 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-08-14 | |
dc.identifier.citation | [1] J. Almazan, B. Gajic, N. Murray, and D. Larlus. Re-id done right: towards good practices for person re-identification. arXiv preprint arXiv:1801.05339, 2018.
[2] W. Chen, X. Chen, J. Zhang, and K. Huang. Beyond triplet loss: a deep quadruplet network for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 403–412, 2017. [3] J. Deng, J. Guo, N. Xue, and S. Zafeiriou. Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4690–4699, 2019. [4] E. Dodds, H. Nguyen, S. Herdade, J. Culpepper, A. Kae, and P. Garrigues. Learning embeddings for product visual search with triplet loss and online sampling. arXiv preprint arXiv:dodds2018learning, 2018. [5] M. Engilberge, L. Chevallier, P. Pérez, and M. Cord. Sodeep: a sorting deep net to learn ranking loss surrogates. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 10792–10801, 2019. [6] B. Gajic and R. Baldrich. Cross-domain fashion image retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 1869–1871, 2018. [7] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. [8] A. Hermans, L. Beyer, and B. Leibe. In defense of the triplet loss for person reidentification. arXiv preprint arXiv:1703.07737, 2017. [9] G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 07-49, University of Massachusetts, Amherst, October 2007. [10] W. Li, R. Zhao, T. Xiao, and X. Wang. Deepreid: Deep filter pairing neural network for person re-identification. In CVPR, 2014. [11] Z. Liu, P. Luo, S. Qiu, X. Wang, and X. Tang. Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016. [12] D. G. Lowe et al. Object recognition from local scale-invariant features. In iccv, volume 99, pages 1150–1157, 1999. [13] E. Ristani, F. Solera, R. Zou, R. Cucchiara, and C. Tomasi. Performance measures and a data set for multi-target, multi-camera tracking. In European Conference on Computer Vision workshop on Benchmarking Multi-Target Tracking, 2016. [14] E. Ristani and C. Tomasi. Features for multi-target multi-camera tracking and reidentification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6036–6046, 2018. [15] F. Schroff, D. Kalenichenko, and J. Philbin. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 815–823, 2015. [16] C. Su, J. Li, S. Zhang, J. Xing, W. Gao, and Q. Tian. Pose-driven deep convolutional model for person re-identification. In Proceedings of the IEEE International Conference on Computer Vision, pages 3960–3969, 2017. [17] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1–9, 2015. [18] X. Wang, Y. Hua, E. Kodirov, G. Hu, R. Garnier, and N. M. Robertson. Ranked list loss for deep metric learning. arXiv preprint arXiv:1903.03238, 2019. [19] K. Q. Weinberger and L. K. Saul. Distance metric learning for large margin nearest neighbor classification. Journal of Machine Learning Research, 10(Feb):207–244, 2009. [20] Y. Wen, K. Zhang, Z. Li, and Y. Qiao. A discriminative feature learning approach for deep face recognition. In European conference on computer vision, pages 499–515. Springer, 2016. [21] L. Wolf, T. Hassner, and I. Maoz. Face recognition in unconstrained videos with matched background similarity. IEEE, 2011. [22] Q. Xiao, H. Luo, and C. Zhang. Margin sample mining loss: A deep learning based method for person re-identification. arXiv preprint arXiv:1710.00478, 2017. [23] L. Zheng, Y. Huang, H. Lu, and Y. Yang. Pose invariant embedding for deep person re-identification. IEEE Transactions on Image Processing, 2019. [24] L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian. Scalable person reidentification: A benchmark. In Computer Vision, IEEE International Conference on, 2015. [25] Z. Zheng, L. Zheng, and Y. Yang. Unlabeled samples generated by gan improve the person re-identification baseline in vitro. arXiv preprint arXiv:1701.07717, 2017. [26] Z. Zhong, L. Zheng, D. Cao, and S. Li. Re-ranking person re-identification with k-reciprocal encoding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1318–1327, 2017. [27] Z. Zhong, L. Zheng, G. Kang, S. Li, and Y. Yang. Random erasing data augmentation. arXiv preprint arXiv:1708.04896, 2017. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74045 | - |
dc.description.abstract | 三元子損失函數被廣泛地使用在基於內容的圖像檢索和深度量度學習之中。然而,要達到良好的訓練效果,往往必須反覆實驗已取得最好的超參數。這篇論文使用各個樣本間的排名資訊以解決這項問題。我們是用了排名值的軟性估計,並藉此提出了軟性排名閾值損失函數。我們的損失函數目標在最小化正樣本間的排名值直到其小於某個給定的閾值,同時最大化副樣本間的排名值直到其大於某個給定的閾值。為求更進步的表現,我們提出了一種難例挖掘技巧,藉由推移某些負樣本間的距離已達到更好的訓練效果。我們的實驗顯示,我們的損失函數在行人重識別和衣物檢索上的資料集都打敗了其他損失函數。我們提出的損失函數亦可以被使用在其他圖像檢索的課題上。 | zh_TW |
dc.description.abstract | Triplet losses have been widely used in content-based image retrieval and deep metric learning. However, it usually suffers the problems of setting some hyper-parameters which require repeated tests. This thesis uses the information of the rank between samples in a single batch to tackle this problem. We introduce the soft ranking threshold loss, which utilizes the soft approximation of such ranking values. Our loss aims to minimize the ranking value of anchor-positive pair to be less than a given threshold and maximize the ranking value of anchor-negative pair to be greater than a given threshold. To further improve the performance of our loss, we also propose a hard mining technique by shifting the distances of anchor-negative pairs. We show that our loss outperforms other losses on both person re-identification and fashion retrieval. The proposed loss can also be applied to other content-based image retrieval tasks. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T08:17:53Z (GMT). No. of bitstreams: 1 ntu-108-R06944007-1.pdf: 1534991 bytes, checksum: 5aa15901dde4d20a3474c15b8ead535c (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | 誌謝i
摘要ii Abstract iii 1 Introduction 1 2 Related Work 5 2.1 Content-based Image Retrieval . . . . . . . . . . . . . . . . . . . . . . . 5 2.2 Person Re-identification . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.3 Fashion Retrieval . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.4 Ranking-based Research . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.5 Deep Metric Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.5.1 Large Margin Nearest Neighbor Loss . . . . . . . . . . . . . . . 7 2.5.2 Triplet Loss . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.5.3 Batch Hard Triplet Loss . . . . . . . . . . . . . . . . . . . . . . 8 2.5.4 Adaptive Weighted Triplet Loss . . . . . . . . . . . . . . . . . . 8 3 Approach 10 3.1 Soft Ranking . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.1.1 Rank . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.1.2 Hard Ranking . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.1.3 Soft Ranking . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.2 Soft Ranking Losses . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.2.1 Threshold Loss . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.2.2 Rank Margin . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 3.3 Shifting Distance Hard Mining . . . . . . . . . . . . . . . . . . . . . . . 15 4 Experiments 17 4.1 Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.1.1 Market1501 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.1.2 CUHK03 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.1.3 DukeMTMC . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.1.4 DeepFashion . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.2 Model Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.3 Implementation Details . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 4.4 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.5 Soft Ranking Losses . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 4.5.1 The Effect of Alpha . . . . . . . . . . . . . . . . . . . . . . . . 20 4.5.2 The Effect of Rank Margin . . . . . . . . . . . . . . . . . . . . . 20 4.6 Shifting Distance Hard-mining . . . . . . . . . . . . . . . . . . . . . . . 21 4.7 Comparison to State-of-the-Art Losses . . . . . . . . . . . . . . . . . . . 22 5 Conclusion 23 Bibliography 24 | |
dc.language.iso | en | |
dc.title | 基於軟性排名損失函數之圖像相似度估測 | zh_TW |
dc.title | Soft Ranking Losses for Deep Image Similarity Estimation | en |
dc.type | Thesis | |
dc.date.schoolyear | 107-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 林彥宇(Yen-Yu Lin) | |
dc.contributor.oralexamcommittee | 王鈺強,陳駿丞 | |
dc.subject.keyword | 深度度量學習,圖像檢索, | zh_TW |
dc.subject.keyword | deep metric learning,image retrieval, | en |
dc.relation.page | 27 | |
dc.identifier.doi | 10.6342/NTU201903394 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2019-08-14 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
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-108-1.pdf 目前未授權公開取用 | 1.5 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。