Unsupervised Domain Adaptation Deep Network Based on Discriminative Class-Wise MMD

doi:10.3934/math.2024323

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 987654321/125031

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/987654321/125031

题名:	Unsupervised Domain Adaptation Deep Network Based on Discriminative Class-Wise MMD
作者:	Lin, Hsiau-Wen;Tsai, Yihjia;Lin, Hwei Jen;Yu, Chen-Hsiang;Liu, Meng-Hsing
关键词:	maximum mean discrepancy (MMD);unsupervised domain adaptation;transfer learning;reproduced kernel Hilbert space;pseudo labels
日期:	2024-02-06
上传时间:	2024-02-20 12:05:37 (UTC+8)
出版者:	AIMS Press
摘要:	General learning algorithms trained on a specific dataset often have difficulty generalizing effectively across different domains. In traditional pattern recognition, a classifier is typically trained on one dataset and then tested on another, assuming both datasets follow the same distribution. This assumption poses difficulty for the solution to be applied in real-world scenarios. The challenge of making a robust generalization from data originated from diverse sources is called the domain adaptation problem. Many studies have suggested solutions for mapping samples from two domains into a shared feature space and aligning their distributions. To achieve distribution alignment, minimizing the maximum mean discrepancy (MMD) between the feature distributions of the two domains has been proven effective. However, this alignment of features between two domains ignores the essential class-wise alignment, which is crucial for adaptation. To address the issue, this study introduced a discriminative, class-wise deep kernel-based MMD technique for unsupervised domain adaptation. Experimental findings demonstrated that the proposed approach not only aligns the data distribution of each class in both source and target domains, but it also enhances the adaptation outcomes.
關聯:	AIMS Mathematics 9(3), p.6628–6647
DOI:	10.3934/math.2024323
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	90	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.....