請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/82317完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳祝嵩(Chu-Song Chen) | |
| dc.contributor.author | Shr-Tze Wan | en |
| dc.contributor.author | 萬世澤 | zh_TW |
| dc.date.accessioned | 2022-11-25T07:29:08Z | - |
| dc.date.available | 2022-12-31 | |
| dc.date.copyright | 2021-08-20 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-08-05 | |
| dc.identifier.citation | R. Aljundi, M. Lin, B. Goujaud, and Y. Bengio. Gradient based sample selection for online continual learning. In NeurIPS, 2019. Y. Bai, Y. Chen, W. Yu, L. Wang, and W. Zhang. Products-10k: A large-scale product recognition dataset. arXiv preprint arXiv:2008.10545, 2020. J. Bang, H. Kim, Y. Yoo, J.-W. Ha, and J. Choi. Rainbow memory: Continual learning with a memory of diverse samples. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8218– 8227, June 2021. P. P. Brahma and A. Othon. Subset replay based continual learning for scalable improvement of autonomous systems. 2018 IEEE/CVF Conference on Com- puter Vision and Pattern Recognition Workshops (CVPRW), pages 1179–11798, 2018. M. Budnik and Y. Avrithis. Asymmetric metric learning for knowledge transfer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8228–8238, June 2021. F. M. Castro, M. J. Marin-Jimenez, N. Guil, C. Schmid, and K. Alahari. End- to-end incremental learning. In Proceedings of the European Conference on Computer Vision (ECCV), September 2018. A. Chaudhry, P. K. Dokania, T. Ajanthan, and P. H. S. Torr. Riemannian walk for incremental learning: Understanding forgetting and intransigence. In Pro- ceedings of the European Conference on Computer Vision (ECCV), September 2018. K. Chen, Y. Wu, H. Qin, D. Liang, X. Liu, and J. Yan. R3 adversarial network for cross model face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019. W. Chen, Y. Liu, W. Wang, T. Tuytelaars, E. M. Bakker, and M. Lew. On the exploration of incremental learning for fine-grained image retrieval. In 31st British Machine Vision Conference 2020, BMVC 2020, Virtual Event, UK, September 7-10, 2020. BMVA Press, 2020. E. D. Cubuk, B. Zoph, D. Mane, V. Vasudevan, and Q. V. Le. Autoaugment: Learning augmentation strategies from data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019. E. D. Cubuk, B. Zoph, J. Shlens, and Q. V. Le. Randaugment: Practical automated data augmentation with a reduced search space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2020. J. Deng, J. Guo, and S. Zafeiriou. Arcface: Additive angular margin loss for deep face recognition. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4685–4694, 2019. P. Dhar, R. V. Singh, K.-C. Peng, Z. Wu, and R. Chellappa. Learning without memorizing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019. A. Douillard, M. Cord, C. Ollion, T. Robert, and E. Valle. Podnet: Pooled outputs distillation for small-tasks incremental learning. In Computer Vision– ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XX 16, pages 86–102. Springer, 2020. R. French. Catastrophic forgetting in connectionist networks. Trends in cogni- tive sciences, 3(4):128—135, April 1999. Google. Google trends. https://trends.google.com, accessed 2021-07-15. I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. C. Courville. Im- proved training of wasserstein gans. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017. R. Hadsell, S. Chopra, and Y. LeCun. Dimensionality reduction by learning an invariant mapping. 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), 2:1735–1742, 2006. T. L. Hayes, N. D. Cahill, and C. Kanan. Memory efficient experience replay for streaming learning. In International Conference on Robotics and Automation (ICRA). IEEE, 2019. K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recogni- tion. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016. A. Hermans, L. Beyer, and B. Leibe. In defense of the triplet loss for person re-identification. ArXiv, abs/1703.07737, 2017. S. Hou, X. Pan, C. C. Loy, Z. Wang, and D. Lin. Learning a unified classifier incrementally via rebalancing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019. H. Hu, Y. Wang, L. Yang, P. Komlev, L. Huang, X. Chen, J. Huang, Y. Wu, M. Merchant, and A. Sacheti. Web-scale responsive visual search at bing. Pro- ceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery Data Mining, 2018. H. J ́egou, M. Douze, and C. Schmid. Product quantization for nearest neigh- bor search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33:117–128, 2011. Y. Jing, D. C. Liu, D. Kislyuk, A. Zhai, J. Xu, J. Donahue, and S. Tavel. Visual search at pinterest. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015. H. J ́egou, M. Douze, C. Schmid, and P. P ́erez. Aggregating local descriptors into a compact image representation. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 3304–3311, 2010. A. Khosla, N. Jayadevaprakash, B. Yao, and L. Fei-Fei. Novel dataset for fine-grained image categorization. In First Workshop on Fine-Grained Visual Categorization, IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, June 2011. J. Kirkpatrick, R. Pascanu, N. C. Rabinowitz, J. Veness, G. Desjardins, A. A. Rusu, K. Milan, J. Quan, T. Ramalho, A. Grabska-Barwinska, D. Hassabis, C. Clopath, D. Kumaran, and R. Hadsell. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences, 114:3521 – 3526, 2017. A. Krizhevsky and G. Hinton. Learning multiple layers of features from tiny im- ages. Master’s thesis, Department of Computer Science, University of Toronto, 2009. Y. Le and X. Yang. Tiny imagenet visual recognition challenge. 2015. Z. Li and D. Hoiem. Learning without forgetting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40:2935–2947, 2018. W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj, and L. Song. Sphereface: Deep hyper- sphere embedding for face recognition. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 6738–6746, 2017. Y. Liu, Y. Su, A.-A. Liu, B. Schiele, and Q. Sun. Mnemonics training: Multi- class incremental learning without forgetting. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020. I. Loshchilov and F. Hutter. SGDR: stochastic gradient descent with warm restarts. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. Open- Review.net, 2017. D. Lowe. Object recognition from local scale-invariant features. Proceedings of the Seventh IEEE International Conference on Computer Vision, 2:1150–1157 vol.2, 1999. C. Luo, J. Zhan, X. Xue, L. Wang, R. Ren, and Q. Yang. Cosine normal- ization: Using cosine similarity instead of dot product in neural networks. In V. Kurkova ́, Y. Manolopoulos, B. Hammer, L. S. Iliadis, and I. Maglogiannis, editors, Artificial Neural Networks and Machine Learning - ICANN 2018 - 27th International Conference on Artificial Neural Networks, Rhodes, Greece, Octo- ber 4-7, 2018, Proceedings, Part I, volume 11139 of Lecture Notes in Computer Science, pages 382–391. Springer, 2018. M. Mermillod, A. Bugaiska, and P. BONIN. The stability-plasticity dilemma: investigating the continuum from catastrophic forgetting to age-limited learning effects. Frontiers in Psychology, 4:504, 2013. Y. Movshovitz-Attias, A. Toshev, T. Leung, S. Ioffe, and S. Singh. No fuss distance metric learning using proxies. 2017 IEEE International Conference on Computer Vision (ICCV), pages 360–368, 2017. K. Musgrave, S. J. Belongie, and S.-N. Lim. A metric learning reality check. In ECCV, 2020. A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga, and A. Lerer. Automatic differentiation in pytorch. In Advances in Neural Information Processing Systems Workshops, 2017. F. Perronnin, Y. Liu, J. Sa ́nchez, and H. Poirier. Large-scale image retrieval with compressed fisher vectors. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 3384–3391, 2010. Q. Qian, L. Shang, B. Sun, J. Hu, H. Li, and R. Jin. Softtriple loss: Deep metric learning without triplet sampling. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pages 6449–6457, 2019. A. Rannen, R. Aljundi, M. B. Blaschko, and T. Tuytelaars. Encoder based lifelong learning. In Proceedings of the IEEE International Conference on Com- puter Vision (ICCV), Oct 2017. S.-A. Rebuffi, A. Kolesnikov, G. Sperl, and C. H. Lampert. icarl: Incremental classifier and representation learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017. K. Roth, T. Milbich, S. Sinha, P. Gupta, B. Ommer, and J. P. Cohen. Revisiting training strategies and generalization performance in deep metric learning. In H. D. III and A. Singh, editors, Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 8242–8252. PMLR, 13–18 Jul 2020. F. Schroff, D. Kalenichenko, and J. Philbin. Facenet: A unified embedding for face recognition and clustering. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 815–823, 2015. J. Schwarz, W. Czarnecki, J. Luketina, A. Grabska-Barwinska, Y. W. Teh, R. Pascanu, and R. Hadsell. Progress compress: A scalable framework for continual learning. In International Conference on Machine Learning, pages 4528–4537. PMLR, 2018. R. R. Selvaraju, A. Das, R. Vedantam, M. Cogswell, D. Parikh, and D. Ba- tra. Grad-cam: Visual explanations from deep networks via gradient-based localization. International Journal of Computer Vision, 128:336–359, 2019. Y. Shen, Y. Xiong, W. Xia, and S. Soatto. Towards backward-compatible repre- sentation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020. H. Shin, J. K. Lee, J. Kim, and J. Kim. Continual learning with deep generative replay. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vish- wanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017. J. Sivic and A. Zisserman. Video google: a text retrieval approach to ob- ject matching in videos. Proceedings Ninth IEEE International Conference on Computer Vision, pages 1470–1477 vol.2, 2003. K. Sohn. Improved deep metric learning with multi-class n-pair loss objective. In NIPS, 2016. H. O. Song, Y. Xiang, S. Jegelka, and S. Savarese. Deep metric learning via lifted structured feature embedding. 2016 IEEE Conference on Computer Vi- sion and Pattern Recognition (CVPR), pages 4004–4012, 2016. Y. Sun, Y. Chen, X. Wang, and X. Tang. Deep learning face representation by joint identification-verification. In NIPS, 2014. Y. Sun, X. Wang, and X. Tang. Deep learning face representation from pre- dicting 10,000 classes. 2014 IEEE Conference on Computer Vision and Pattern Recognition, pages 1891–1898, 2014. E. W. Teh, T. Devries, and G. W. Taylor. Proxynca++: Revisiting and revi- talizing proxy neighborhood component analysis. In ECCV, 2020. G. Van Horn, O. Mac Aodha, Y. Song, Y. Cui, C. Sun, A. Shepard, H. Adam, P. Perona, and S. Belongie. The inaturalist species classification and detec- tion dataset. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018. C. Wang, Y. Chang, S. Yang, D. Chen, and S. Lai. Unified representation learn- ing for cross model compatibility. In 31st British Machine Vision Conference 2020, BMVC 2020, Virtual Event, UK, September 7-10, 2020. BMVA Press, 2020. H. Wang, Y. Wang, Z. Zhou, X. Ji, Z. Li, D. Gong, J. Zhou, and W. Liu. Cosface: Large margin cosine loss for deep face recognition. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5265–5274, 2018. X. Wang, X. Han, W. Huang, D. Dong, and M. R. Scott. Multi-similarity loss with general pair weighting for deep metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019. X. Wang, H. Zhang, W. Huang, and M. R. Scott. Cross-batch memory for embedding learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020. Y. Wen, K. Zhang, Z. Li, and Y. Qiao. A discriminative feature learning approach for deep face recognition. In ECCV, 2016. C.-Y. Wu, R. Manmatha, A. J. Smola, and P. Krahenbuhl. Sampling matters in deep embedding learning. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), Oct 2017. D. Wu, Q. Dai, J. Liu, B. Li, and W. Wang. Deep incremental hashing network for efficient image retrieval. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019. H. Xuan, A. Stylianou, and R. Pless. Improved embeddings with easy posi- tive triplet mining. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), March 2020. F. Zenke, B. Poole, and S. Ganguli. Continual learning through synaptic intel- ligence. Proceedings of machine learning research, 70:3987–3995, 2017. C. Zeno, I. Golan, E. Hoffer, and D. Soudry. Task agnostic continual learning using online variational bayes with fixed-point updates. ArXiv, abs/2010.00373, 2020. A. Zhai and H.-Y. Wu. Classification is a strong baseline for deep metric learning. In BMVC, 2019. J. Zhang, J. Zhang, S. Ghosh, D. Li, S. Tasci, L. Heck, H. Zhang, and C.- C. J. Kuo. Class-incremental learning via deep model consolidation. 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 1120–1129, 2020. Y. Zhang, P. Pan, Y. Zheng, K. Zhao, Y. Zhang, X. Ren, and R. Jin. Vi- sual search at alibaba. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery Data Mining, 2018. B. Zhao, S. Tang, D. Chen, H. Bilen, and R. Zhao. Continual representation learning for biometric identification. 2021 IEEE Winter Conference on Appli- cations of Computer Vision (WACV), pages 1197–1207, 2021. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/82317 | - |
| dc.description.abstract | 視覺搜尋旨從圖庫中找出與查詢影像相似的目標，在電子商務系統中扮演著至關重要的角色。隨著電腦視覺技術之演進，深度神經網路透過捕捉深層語意特徵，在視覺搜尋領域取得重大的突破。然而，當今的方法仰賴模型在整個資料集進行訓練，忽略模型持續更新之需求；再者，隨著模型的更迭，新模型必須對圖庫集重新提取特徵，藉以維持在一致的特徵空間中進行合理的成對距離度量，但對於實務而言，陳舊的圖庫集往往過於龐大，致使每輪更新需付出極高的計算代價。本論文基於視覺搜尋提出一種兼顧回溯一致性特徵的持續學習框架，力圖有效緩解上述問題。請注意，在實際的檢索系統中，由於收集的新數據將逐步放入資料庫中，所以圖庫集將漸進增長，我們首創的持續學習方法解決了帶有回溯一致性的圖庫集增長問題，亦即是先前學習器提取的特徵將保持不變，因此，我們的方法不需要對整個圖庫集重新提取特徵。我們引入三個準則來解決這個問題：基於新數據的分類損失、新舊模型之間的蒸餾損失以及迫使圖庫集特徵不變的一致性損失。廣泛的實驗表明該法在所有設置下皆有最頂尖的效能。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-25T07:29:08Z (GMT). No. of bitstreams: 1 U0001-0408202112313900.pdf: 14484824 bytes, checksum: 7c1b91abac991bbb0dac1e90d209df32 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 口試委員會審定書 i 誌謝 ii 中文摘要 iii Abstract iv 1 Introduction 1 1.1 Motivation................................. 1 1.2 Thesis Organization............................ 5 2 Related Work 6 2.1 Image Retrieval.............................. 6 2.2 Continua lLearning............................ 9 2.3 Discussion................................. 11 3 Method 13 3.1 Problem Background ........................... 13 3.2 Problem Formulation........................... 14 3.3 Framework Structure........................... 17 3.3.1 Classification Loss ........................ 18 3.3.2 Distillation Loss.......................... 18 3.3.3 Gallery Embedding Invariance Constraint . . . . . . . . . . . 19 3.3.4 Summary ............................. 20 4 Experiments 22 4.1 Datasets.................................. 22 4.2 Data Distribution for Each Incremental Scenario . . . . . . . . . . . . 25 4.2.1 DisjointSetup........................... 25 4.2.2 BlurrySetup ........................... 25 4.2.3 GeneralSetup........................... 25 4.3 ImplementationDetails.......................... 26 4.3.1 Evaluation............................. 28 4.4 Results on the Coarse-grained Datasets................. 29 4.4.1 Results on CIFAR100....................... 29 4.4.2 Results on TinyImageNet .................... 30 4.5 Results on the Fine-grained Datasets .................. 32 4.5.1 Results on Dog .......................... 34 4.5.2 Results on iNat-M ........................ 34 4.5.3 Results on Product-M ...................... 34 4.6 Discussion................................. 36 4.7 Ablation Study .............................. 39 5 Conclusion 42 Bibliography 43 | |
| dc.language.iso | en | |
| dc.subject | 影像檢索 | zh_TW |
| dc.subject | 永續學習 | zh_TW |
| dc.subject | 特徵一致性學習 | zh_TW |
| dc.subject | 視覺搜尋 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | Feature Consistent Learning | en |
| dc.subject | Visual Search | en |
| dc.subject | Image Retrieval | en |
| dc.subject | Deep Learning | en |
| dc.subject | Continual Learning | en |
| dc.title | 兼顧回溯一致性特徵的持續學習方法於視覺搜尋之研究 | zh_TW |
| dc.title | Continual Learning for Visual Search with Backward Consistent Feature Embedding | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 洪一平(Hsin-Tsai Liu),葉梅珍(Chih-Yang Tseng),陳駿丞 | |
| dc.subject.keyword | 深度學習,永續學習,特徵一致性學習,視覺搜尋,影像檢索, | zh_TW |
| dc.subject.keyword | Deep Learning,Continual Learning,Feature Consistent Learning,Visual Search,Image Retrieval, | en |
| dc.relation.page | 50 | |
| dc.identifier.doi | 10.6342/NTU202102071 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2021-08-05 | |
| 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 |
| dc.date.embargo-lift | 2022-12-31 | - |
| 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 | |
|---|---|---|---|
| U0001-0408202112313900.pdf | 14.15 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。