MeTa Learning-Based Optimization of Unsupervised Domain Adaptation Deep Networks

MeTa Learning-Based Optimization of Unsupervised Domain Adaptation Deep Networks

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 struggl...

Full description

Saved in:
Bibliographic Details
Main Authors: Hsiau-Wen Lin, Trang-Thi Ho, Ching-Ting Tu, Hwei-Jen Lin, Chen-Hsiang Yu
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Mathematics
Subjects:
unsupervised domain adaptation
maximum mean discrepancy (MMD)
discriminative class-wise MMD (DCWMMD)
meta-learning
deep kernel
feature distributions
Online Access:https://www.mdpi.com/2227-7390/13/2/226
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items