MeTa Learning-Based Optimization of Unsupervised Domain Adaptation Deep Networks

doi:10.3390/math13020226

淡江大學機構典藏 > 工學院 > 資訊工程學系暨研究所 > 期刊論文 > Item 987654321/126653

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/126653

题名:	MeTa Learning-Based Optimization of Unsupervised Domain Adaptation Deep Networks
作者:	Hsiau-Wen Lin, Trang-Thi Ho, Ching-Ting Tu, Hwei Jen Lin, Chen-Hsiang Yu
关键词:	unsupervised domain adaptation;maximum mean discrepancy (MMD);discriminative class-wise MMD (DCWMMD);meta-learning;deep kernel;feature distributions;domain shift;transfer learning
日期:	Jan. 10,
上传时间:	2025-01-15 12:05:16 (UTC+8)
摘要:	This paper introduces a novel unsupervised domain adaptation (UDA) method, MeTa Discriminative Class-Wise MMD (MCWMMD), which combines meta-learning with a Class-Wise Maximum Mean Discrepancy (MMD) approach to enhance domain adaptation. Traditional MMD methods align overall distributions but struggle with classwise alignment, reducing feature distinguishability. MCWMMD incorporates a metamodule to dynamically learn a deep kernel for MMD, improving alignment accuracy and model adaptability. This meta-learning technique enhances the model’s ability to generalize across tasks by ensuring domain-invariant and class-discriminative feature representations. Despite the complexity of the method, including the need for meta-module training, it presents a significant advancement in UDA. Future work will explore scalability in diverse real-world scenarios and further optimize the meta-learning framework. MCWMMD offers a promising solution to the persistent challenge of domain adaptation, paving the way for more adaptable and generalizable deep learning models.
關聯:	Mathematics, 13(2):226
DOI:	10.3390/math13020226
显示于类别:	[資訊工程學系暨研究所] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	57	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章

数据加载中.....