請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87177
標題: | 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 LaSER: Improving Class-Imbalanced Semi-Supervised Learning with Label Shift Estimation and Reweighting |
作者: | 黃品硯 Pin-Yen Huang |
指導教授: | 項潔 Jieh Hsiang |
關鍵字: | 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, machine learning,semi-supervised learning,imbalanced learning,label shift estimation,image classification,class-imbalanced semi-supervised learning, |
出版年 : | 2023 |
學位: | 碩士 |
摘要: | 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。 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. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87177 |
DOI: | 10.6342/NTU202300472 |
全文授權: | 未授權 |
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。