Journal Article

MeTa Learning-Based Optimization of Unsupervised Domain Adaptation Deep Networks

Yu, Chen-Hsiang, Lin, Hsiau-Wen, Tu, Ching-Ting, Ho, Trang-Thi, Lin, Hwei-Jen

2025

Overview

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 class-wise alignment, reducing feature distinguishability. MCWMMD incorporates a meta-module 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.

• Publisher: MDPI AG
• Subject: Adaptability / Adaptation / Algorithms / Alignment / Datasets / deep kernel / Deep learning / discriminative class-wise MMD (DCWMMD) / feature distributions / Hilbert space / Machine learning / Mathematical optimization / Mathematical research / maximum mean discrepancy (MMD) / meta-learning / Modules / Neural networks / Optimization / Task complexity / unsupervised domain adaptation