請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87177
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 項潔 | zh_TW |
dc.contributor.advisor | Jieh Hsiang | en |
dc.contributor.author | 黃品硯 | zh_TW |
dc.contributor.author | Pin-Yen Huang | en |
dc.date.accessioned | 2023-05-18T16:11:52Z | - |
dc.date.available | 2023-11-09 | - |
dc.date.copyright | 2023-05-10 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-02-15 | - |
dc.identifier.citation | [1] A. Alexandari, A. Kundaje, and A. Shrikumar. Maximum likelihood with bias corrected calibration is hard-to-beat at label shift adaptation. In International Conference on Machine Learning, pages 222–232. PMLR, 2020.
[2] K. Azizzadenesheli, A. Liu, F. Yang, and A. Anandkumar. Regularized learning for domain adaptation under label shifts. In International Conference on Learning Representations, 2018. [3] D. Berthelot, N. Carlini, E. D. Cubuk, A. Kurakin, K. Sohn, H. Zhang, and C. Raffel. Remixmatch: Semi-supervised learning with distribution matching and augmentation anchoring. In International Conference on Learning Representations, 2019. [4] D. Berthelot, N. Carlini, I. Goodfellow, N. Papernot, A. Oliver, and C. A. Raffel. Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems, 32, 2019. [5] K. Cao, C. Wei, A. Gaidon, N. Arechiga, and T. Ma. Learning imbalanced datasets with label-distribution-aware margin loss. Advances in neural information processing systems, 32, 2019. [6] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer. Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357, 2002. [7] H.-P. Chou, S.-C. Chang, J.-Y. Pan, W. Wei, and D.-C. Juan. Remix: rebalanced mixup. In European Conference on Computer Vision, pages 95–110. Springer, 2020. [8] A. Coates, A. Ng, and H. Lee. An analysis of single-layer networks in unsupervised feature learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics, pages 215–223. JMLR Workshop and Conference Proceedings, 2011. [9] E. D. Cubuk, B. Zoph, D. Mane, V. Vasudevan, and Q. V. Le. Auto augment: Learning augmentation strategies from data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019. [10] Y. Cui, M. Jia, T.-Y. Lin, Y. Song, and S. Belongie. Class-balanced loss based on effective number of samples. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9268–9277, 2019. [11] L.-Z. Guo and Y.-F. Li. Class-imbalanced semi-supervised learning with adaptive thresholding. In International Conference on Machine Learning, pages 8082–8094. PMLR, 2022. [12] J. Kim, Y. Hur, S. Park, E. Yang, S. J. Hwang, and J. Shin. Distribution aligning refinery of pseudo-label for imbalanced semi-supervised learning. Advances in neural information processing systems, 33:14567–14579, 2020. [13] A. Krizhevsky et al. Learning multiple layers of features from tiny images. 2009. [14] Z. Lai, C. Wang, H. Gunawan, S.-C. S. Cheung, and C.-N. Chuah. Smoothed adaptive weighting for imbalanced semi-supervised learning: Improve reliability against unknown distribution data. In International Conference on Machine Learning, pages 11828–11843. PMLR, 2022. [15] D.-H. Lee et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, volume 3, page 896, 2013. [16] H. Lee, S. Shin, and H. Kim. Abc: Auxiliary balanced classifier for class-imbalanced semi-supervised learning. Advances in Neural Information Processing Systems, 34:7082–7094, 2021. [17] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740–755. Springer, 2014. [18] Z. Lipton, Y.-X. Wang, and A. Smola. Detecting and correcting for label shift with black box predictors. In International conference on machine learning, pages 3122–3130. PMLR, 2018. [19] Z. Liu, Z. Miao, X. Zhan, J. Wang, B. Gong, and S. X. Yu. Large-scale longtailed recognition in an open world. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2537–2546, 2019. [20] Y. Oh, D.-J. Kim, and I. S. Kweon. Daso: Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9786–9796, 2022. [21] K. Sohn, D. Berthelot, N. Carlini, Z. Zhang, H. Zhang, C. A. Raffel, E. D. Cubuk, A. Kurakin, and C.-L. Li. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, 33:596–608, 2020. [22] C. Wei, K. Sohn, C. Mellina, A. Yuille, and F. Yang. Crest: A class-rebalancing self-training framework for imbalanced semi-supervised learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10857–10866, 2021. [23] Q. Xie, Z. Dai, E. Hovy, T. Luong, and Q. Le. Unsupervised data augmentation for consistency training. Advancesin Neural Information Processing Systems, 33:6256–6268, 2020. [24] B. Zhang, Y. Wang, W. Hou, H. Wu, J. Wang, M. Okumura, and T. Shinozaki. Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. Advances in Neural Information Processing Systems, 34:18408–18419, 2021. [25] H. Zhang, M. Cisse, Y. N. Dauphin, and D. Lopez-Paz. mixup: Beyond empirical risk minimization. In International Conference on Learning Representations, 2018. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87177 | - |
dc.description.abstract | 傳統半監督學習(semi-supervised learning, SSL)的方法假設訓練資料的類別是平均分佈的,也就是說每個類別的訓練資料數量是一樣的。然而,在現實世界的資料中,多數的資料類別是不平均分佈的。這對於傳統的 SSL 演算法是一個重大挑戰,它們在這種情況下通常表現不佳,會嚴重傾向於預測訓練資料較多的類別。為了解決這個問題,有一種研究領域在探討類別不平衡資料下的半監督學習(class-imbalanced semi-supervised learning, CISSL),讓 SSL 演算法可以減少受到不平衡資料造成的影響。我們發現在現有 CISSL 的研究中有兩種方向: (1)提高僞標籤(pseudo-label)的準確度, (2)結合 SSL 與不平衡學習(class-imbalanced learning)。這兩種研究方向解決了不同面向的問題。在本論文中,我們提出了一種結合這兩種流派的新方法,我們的方法分別結合了 DARP 和 Mixup-DRW 到現有的 SSL 演算法中。此外,我們改進了在不平衡資料下的標註分佈預測(label shift estimation, LSE),更進一步在各種環境、設定下提高了 SSL 性能和穩定性。 | zh_TW |
dc.description.abstract | The field of semi-supervised learning (SSL) has traditionally relied on the assumption that the class distribution of training data is evenly distributed. However, real-world datasets often have imbalanced or long-tailed distributions. This poses a significant challenge for traditional SSL, as they tend to exhibit poor performance in such conditions. To address this problem, a variant of SSL known as class-imbalanced semi-supervised learning (CISSL) has been introduced. CISSL is specifically designed to be more robust against imbalanced data. We found there are two approaches in existing works of CISSL: (1) enhancing the quality of pseudo-labels, and (2) adapting imbalanced learning techniques to SSL. The two approaches address different aspects of the problem. In this thesis, we propose a novel method that combines two approaches, namely DARP and Mixup-DRW. Additionally, we improve the existing label shift estimation (LSE) in CISSL settings. Resulting in enhanced performance and robustness of SSL under various conditions. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-05-18T16:11:52Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2023-05-18T16:11:52Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | Acknowledgements iii
摘要 v Abstract vii Contents ix List of Figures xi List of Tables xiii Denotation xv Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Class-Imbalanced Semi-Supervised Learning 1 1.3 Contribution 4 1.4 Overview 5 Chapter 2 Literature Review 7 2.1 Semi-supervised learning 7 2.2 Class-imbalanced learning 9 2.3 Class-imbalanced semi-supervised learning 9 2.4 Label shift estimation 10 Chapter 3 Methods 13 3.1 Problem setup 13 3.2 Method 15 3.2.1 ReMixMatch 16 3.2.2 DRW 18 3.2.3 DARP 19 3.3 Label shift estimation under CISSL 20 3.3.1 Mixup-DRW 20 3.3.2 Deep Ensemble Learning 20 Chapter 4 Experiments 23 4.1 CIFAR10 Dataset 24 4.2 STL10 Dataset 25 4.3 LSE Results 26 4.4 CISSL Results 27 Chapter 5 Conclusion 31 5.1 Summary 31 5.2 Future works 32 References 33 | - |
dc.language.iso | en | - |
dc.title | LaSER: 基於分布預測與權重調整改善不平衡資料下之半監督式學習之框架 | zh_TW |
dc.title | LaSER: Improving Class-Imbalanced Semi-Supervised Learning with Label Shift Estimation and Reweighting | en |
dc.type | Thesis | - |
dc.date.schoolyear | 111-1 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 謝育平;蔡宗翰 | zh_TW |
dc.contributor.oralexamcommittee | Yuh-Pyng Shieh;Tzong-Han Tsai | en |
dc.subject.keyword | 機器學習,半監督式學習,不平衡學習,標註分佈預測,影像分類,不平衡半監督式學習, | zh_TW |
dc.subject.keyword | machine learning,semi-supervised learning,imbalanced learning,label shift estimation,image classification,class-imbalanced semi-supervised learning, | en |
dc.relation.page | 36 | - |
dc.identifier.doi | 10.6342/NTU202300472 | - |
dc.rights.note | 未授權 | - |
dc.date.accepted | 2023-02-15 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 資訊工程學系 | - |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-111-1.pdf 目前未授權公開取用 | 2.16 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。