請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/86353完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 于天立(Tian-Li Yu) | |
| dc.contributor.author | Ching-Han Chang | en |
| dc.contributor.author | 張景翰 | zh_TW |
| dc.date.accessioned | 2023-03-19T23:50:50Z | - |
| dc.date.copyright | 2022-08-29 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-08-24 | |
| dc.identifier.citation | [1] M. Andrychowicz, M. Denil, S. Gomez, M. W. Hoffman, D. Pfau, T. Schaul, B. Shillingford, and N. de Freitas. Learning to learn by gradient descent by gradient descent. In NeurIPS, 2018. [2] L. Bertinetto, J. F. Henriques, P. Torr, and A. Vedaldi. Meta-learning with differentiable closed-form solvers. In ICLR, 2019. [3] L. Bertinetto, J. F. Henriques, J. Valmadre, P. H. S. Torr, and A. Vedaldi. Learning feed-forward one-shot learners. In NeurIPS, pages 523–531, 2016. [4] W. Brendel and M. Bethge. Approximating cnns with bag-of-local-features models works surprisingly well on imagenet. In ICLR, 2019. [5] Q. Cai, Y. Pan, T. Yao, C. Yan, and T. Mei. Memory matching networks for one-shot image recognition. In CVPR, pages 4080–4088, 2018. [6] K. Cao, M. Brbic, and J. Leskovec. Concept learners for few-shot learning. In ICLR, 2021. [7] L. Chen, H. Zhang, J. Xiao, L. Nie, J. Shao, W. Liu, and T.-S. Chua. Sca- cnn: Spatial and channel-wise attention in convolutional networks for image captioning. In CVPR, pages 5659–5667, 2017. [8] W.-Y. Chen, Y.-C. Liu, Z. Kira, Y.-C. Wang, and J.-B. Huang. A closer look at few-shot classification. In ICLR, 2019. [9] C. Doersch, A. Gupta, and A. Zisserman. Crosstransformers: spatially-aware few-shot transfer. In NeurIPS, 2020. [10] C. Finn, P. Abbeel, and S. Levine. Model-agnostic meta-learning for fast adap- tation of deep networks. In ICML, pages 1126–1135, 2017. [11] P. Gao, P. Lu, H. Li, S. Li, Y. Li, S. Hoi, and X. Wang. Question-guided hybrid convolution for visual question answering. In ECCV, pages 469–485, 2018. [12] R. Geirhos, P. Rubisch, C. Michaelis, M. Bethge, F. A. Wichmann, and W. Brendel. Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. In ICLR, 2019. [13] S. Gidaris, A. Bursuc, N. Komodakis, P. P ́erez, and M. Cord. Boosting few-shot visual learning with self-supervision. In ICCV, 2019. [14] S. Gidaris and N. Komodakis. Dynamic few-shot visual learning without for- getting. In CVPR, pages 4367–4375, 2018. [15] S. Gidaris and N. Komodakis. Generating classification weights with gnn de- noising autoencoders for few-shot learning. In CVPR, 2019. [16] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recog- nition. In CVPR, 2016. [17] T. Hospedales, A. Antoniou, P. Micaelli, and A. Storkey. Meta-learning in neural networks: A survey. 2020. [18] R. Hou, H. Chang, B. Ma, S. Shan, and X. Chen. Cross attention network for few-shot classification. In NeurIPS, 2019. [19] J. Hu, L. Shen, S. Albanie, G. Sun, and E. Wu. Squeeze-and-excitation net- works. 2019. [20] D. Kang, H. Kwon, J. Min, and M. Cho. Relational embedding for few-shot classification. In ICCV, 2021. [21] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In F. Pereira, C. Burges, L. Bottou, and K. Weinberger, editors, NeurIPS, volume 25. Curran Associates, Inc., 2012. [22] K. Lee, S. Maji, A. Ravichandran, and S. Soatto. Meta-learning with differen- tiable convex optimization. In CVPR, 2019. [23] H. Li, D. Eigen, S. Dodge, M. Zeiler, and X. Wang. Finding Task-Relevant Features for Few-Shot Learning by Category Traversal. In CVPR, 2019. [24] W. Li, L. Wang, J. Xu, J. Huo, Y. Gao, and J. Luo. Revisiting local descriptor based image-to-class measure for few-shot learning. In CVPR, 2019. [25] Z. Li, F. Zhou, F. Chen, and H. Li. Meta-sgd: Learning to learn quickly for few-shot learning. 2017. [26] Y. Lifchitz, Y. Avrithis, and S. Picard. Local propagation for few-shot learning. In ICPR, 2021. [27] Y. Lifchitz, Y. Avrithis, S. Picard, and A. Bursuc. Dense classification and implanting for few-shot learning. In CVPR, 2019. [28] B. Liu, Y. Cao, Y. Lin, Q. Li, Z. Zhang, M. Long, and H. Hu. Negative margin matters: Understanding margin in few-shot classification. In ECCV, 2020. [29] Y. Liu, J. Lee, M. Park, S. Kim, E. Yang, S. J. Hwang, and Y. Yang. Learning to propagate labels: Transductive propagation network for few-shot learning. In ICLR, 2018. [30] Y. Liu, B. Schiele, and Q. Sun. An ensemble of epoch-wise empirical bayes for few-shot learning. In ECCV, 2020. [31] P. Mangla, N. Kumari, A. Sinha, M. Singh, B. Krishnamurthy, and V. N. Balasubramanian. Charting the right manifold: Manifold mixup for few-shot learning. In WACV, pages 2218–2227, 2020. [32] N. Mishra, M. Rohaninejad, X. Chen, and P. Abbeel. A simple neural attentive meta-learner. In ICLR, 2018. [33] T. Munkhdalai and H. Yu. Meta networks. In ICML, pages 2554–2563, 2017. [34] T. Munkhdalai, X. Yuan, S. Mehri, and A. Trischler. Rapid adaptation with conditionally shifted neurons. In ICML, 2018. [35] A. Nichol, J. Achiam, and J. Schulman. On first-order meta-learning algorithms. 2018. [36] A. Oliver, A. Odena, C. Raffel, E. D. Cubuk, and I. J. Goodfellow. Realistic evaluation of deep semi-supervised learning algorithms. In NeurIPS, 2018. [37] B. N. Oreshkin, P. Rodriguez, and A. Lacoste. Tadam: Task dependent adaptive metric for improved few-shot learning. In NeurIPS, pages 719–729, 2018. [38] J. Park, S. Woo, J.-Y. Lee, and I. S. Kweon. Bam: Bottleneck attention module. In BMVC, 2018. [39] M. Pedersoli, T. Lucas, C. Schmid, and J. Verbeek. Areas of attention for image captioning. In ICCV, pages 1251–1259, 2017. [40] S. Qiao, C. Liu, W. Shen, and A. L. Yuille. Few-shot image recognition by predicting parameters from activations. In CVPR, 2018. [41] S. Ravi and H. Larochelle. Optimization as a model for few-shot learning. In ICLR, 2017. [42] A. Ravichandran, R. Bhotika, and S. Soatto. Few-shot learning with embedded class models and shot-free meta training. In ICCV, 2019. [43] M. Ren, E. Triantafillou, S. Ravi, J. Snell, K. Swersky, J. B. Tenenbaum, H. Larochelle, and R. S. Zemel. Meta-learning for semi-supervised few-shot classification. In ICLR, 2018. [44] M. Ren, E. Triantafillou, S. Ravi, J. Snell, K. Swersky, J. B. Tenenbaum, H. Larochelle, and R. S. Zemel. Meta-learning for semi-supervised few-shot classification. 2018. [45] A. A. Rusu, D. Rao, J. Sygnowski, O. Vinyals, R. Pascanu, S. Osindero, and R. Hadsell. Meta-learning with latent embedding optimization. In ICLR, 2019. [46] A. Santoro, S. Bartunov, M. Botvinick, D. Wierstra, and T. Lillicrap. One-shot learning with memory-augmented neural networks. In ICML, pages 1842–1850, 2016. [47] J. Snell, K. Swersky, and R. Zemel. Prototypical networks for few-shot learning. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, NeurIPS, volume 30, pages 4077–4087. Curran Asso- ciates, Inc., 2017. [48] Q. Sun, Y. Liu, T.-S. Chua, and B. Schiele. Meta-transfer learning for few-shot learning. In CVPR, 2019. [49] F. Sung, Y. Yang, L. Zhang, T. Xiang, P. H. S. Torr, and T. M. Hospedales. Learning to compare: Relation network for few-shot learning. In CVPR, pages 1199–1208, 2018. [50] Y. Tian, Y. Wang, D. Krishnan, J. B. Tenenbaum, and P. Isola. Rethinking few-shot image classification: a good embedding is all you need? In ECCV, 2020. [51] O. Vinyals, C. Blundell, T. Lillicrap, K. Kavukcuoglu, and D. Wierstra. Match- ing networks for one shot learning. In NeurIPS, pages 3630–3638, 2016. [52] Y. Wang, W.-L. Chao, K. Q. Weinberger, and L. van der Maaten. Simpleshot: Revisiting nearest-neighbor classification for few-shot learning. 2019. [53] Y. Wang, Q. Yao, J. Kwok, and L. M. Ni. Generalizing from a few examples: A survey on few-shot learning. 2019. [54] P. Welinder, S. Branson, T. Mita, C. Wah, F. Schroff, S. Belongie, and P. Per- ona. Caltech-UCSD Birds 200. Technical Report CNS-TR-2010-001, California Institute of Technology, 2010. [55] S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon. Cbam: Convolutional block attention module. In ECCV, pages 3–19, 2018. [56] H. Xu and K. Saenko. Ask, attend and answer: Exploring question-guided spatial attention for visual question answering. In ECCV, pages 451–466, 2016. [57] K. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhutdinov, R. Zemel, and Y. Bengio. Show, attend and tell: Neural image caption generation with visual attention, 2015. [58] Z. Yang, X. He, J. Gao, L. Deng, and A. Smola. Stacked attention networks for image question answering. In CVPR, pages 21–29, 2016. [59] H.-J. Ye, H. Hu, D.-C. Zhan, and F. Sha. Few-shot learning via embedding adaptation with set-to-set functions. In CVPR, pages 8808–8817, 2020. [60] D. Yu, J. Fu, T. Mei, and Y. Rui. Multi-level attention networks for visual question answering. In CVPR, pages 4187–4195, 2017. [61] S. Zagoruyko and N. Komodakis. Paying more attention to attention: Improv- ing the performance of convolutional neural networks via attention transfer. In ICLR, 2017. [62] C. Zhang, Y. Cai, G. Lin, and C. Shen. Deepemd: Few-shot image classification with differentiable earth mover’s distance and structured classifiers. In CVPR, 2020. [63] H. Zhao, J. Jia, and V. Koltun. Exploring self-attention for image recognition. In CVPR, 2020. [64] L. Zhao, X. Li, J. Wang, and Y. Zhuang. Deeply-learned part-aligned repre- sentations for person re-identification. In ICCV, pages 3239–3248, 2017. [65] C. Zheng, T.-J. Cham, and J. Cai. The spatially-correlative loss for various image translation tasks. In CVPR, 2021. [66] Z. Zhong, L. Zheng, G. Kang, S. Li, and Y. Yang. Random erasing data augmentation, 2017. [67] B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba. Learning deep features for discriminative localization. In CVPR, pages 2921–2929, 2016. [68] I. M. Ziko, J. Dolz, E. Granger, and I. B. Ayed. Laplacian regularized few-shot learning. In ICML, 2020. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/86353 | - |
| dc.description.abstract | 小樣本分類具有挑戰性，因為目標是在給予極少量有標籤樣本的情況下對有標籤樣本進行分類。交互關聯已經被證明在小樣本學習上可以產生更具有分辨性的特徵。在relational embedding network (RENet)中，交互關聯已經被用來提取注意力。然而，在RENet中只有利用一張影像本身之內所含有的資訊，如果我們利用兩張影像之間所含有的資訊而不是只有一張影像呢?這篇論文延伸了這個想法，並且提出了三個交互注意模組，分別是cross unscaled attention (CUA)、cross scaled attention (CSA) 和 cross aligned attention (CAA)。明確來說，CUA利用交互關聯幫助模型專注在重要特徵，CSA針對不同特徵圖進行縮放式它們更加完善配對，而CAA則是採用主成分分析使來自不同影像的特徵能夠進一步對齊。我們也為我們的模型發展了兩個end-to-end版本，這兩個版本比較簡單又有效率。實驗證實CUA、CSA和CAA三者全部都能夠在四個小樣本分類廣泛使用的標準數據集上對於最先進的方法取得改善，而CUA略為快速，CAA則是達成較高準確度 | zh_TW |
| dc.description.abstract | Few-shot classification is challenging since the goal is to classify unlabeled samples with very few labeled samples provided. It has been shown that cross correlation helps generate more discriminative features for few-shot learning. In the relational embedding network (RENet), cross correlation has been used to extract attention. However, Only the information contained within an image itself is exploited in RENet. What if we exploit the information contained between two images instead of only one image? This thesis extends the idea and proposes three cross attention modules, namely the cross unscaled attention (CUA), the cross scaled attention (CSA), and the cross aligned attention (CAA). Specifically, CUA exploits cross correlation to help the model focus on important features, and CSA scales different feature maps to make them better matched, and CAA adopts the principal component analysis to further align features from different images. We also develop two end-to-end versions for our model, which are simpler and more efficient. Experiments showed that all CUA, CSA, and CAA achieve consistent improvements over state-of-the-art methods on four widely used few-shot classification benchmark datasets, miniImageNet, tieredImageNet, CIFAR-FS, and CUB-200-2011, while CUA is slightly faster and CAA achieves higher accuracies. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T23:50:50Z (GMT). No. of bitstreams: 1 U0001-2308202211504700.pdf: 5600476 bytes, checksum: 0060eaf8e204afd8dcab0c3d21dd5970 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 誌謝 i 摘要 ii Abstract iii 1 Introduction 1 2 Related Work 5 2.1 RENet . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.1.1 Self-Correlational Representation (SCR) . . . . . . . . . . . . 8 2.1.2 Cross-Correlational Attention (CCA) . . . . . . . . . . . . . . 10 3 Approach 14 3.1 Problem Definition . . . . . . . . . . . . . . . . . . . . . . . . . . .15 3.2 Architecture Overview . . . . . . . . . . . . . . . . . . . . . . . . . 15 3.3 Cross Unscaled Attention (CUA) . . . . . . . . . . . . . . . . . . . . 16 3.4 Cross Scaled Attention (CSA) . . . . . . . . . . . . . . . . . . . . . .19 3.5 Cross Aligned Attention (CAA) . . . . . . . . . . . . . . . . . . . . . 26 3.6 Training and Testing (Inference) . . . . . . . . . . . . . . . . . . . .33 3.7 End-to-end Version . . . . . . . . . . . . . . . . . . . . . . . . . . .35 4 Experiment Results 36 4.1 Experiment Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . .36 4.2 Ablation Study . . . . . . . . . . . . . . . . . . . . . . . . . . . . .40 4.3 End-to-end . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .44 4.4 More Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 5 Conclusion 52 Bibliography 54 | |
| dc.language.iso | en | |
| dc.subject | 小樣本學習 | zh_TW |
| dc.subject | 注意力 | zh_TW |
| dc.subject | 關聯性 | zh_TW |
| dc.subject | 小樣本分類 | zh_TW |
| dc.subject | 元學習 | zh_TW |
| dc.subject | attention | en |
| dc.subject | few-shot classification | en |
| dc.subject | few-shot-learning | en |
| dc.subject | meta-learning | en |
| dc.subject | correlation | en |
| dc.title | 交互關聯:在小樣本學習上改善RENet | zh_TW |
| dc.title | Cross Correlation: An Improvement for RENet on Few-Shot Learning | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 雷欽隆(Chin-Laung Lei),王鈺強(Yu-Chiang Wang) | |
| dc.subject.keyword | 小樣本學習,小樣本分類,元學習,注意力,關聯性, | zh_TW |
| dc.subject.keyword | few-shot-learning,few-shot classification,meta-learning,attention,correlation, | en |
| dc.relation.page | 60 | |
| dc.identifier.doi | 10.6342/NTU202202689 | |
| dc.rights.note | 同意授權(全球公開) | |
| dc.date.accepted | 2022-08-25 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| dc.date.embargo-lift | 2022-08-29 | - |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2308202211504700.pdf | 5.47 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。