4.7 Article

Consistency regularization-based mutual alignment for source-free domain adaptation

期刊

EXPERT SYSTEMS WITH APPLICATIONS
卷 241, 期 -, 页码 -

出版社

PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2023.122577

关键词

Deep learning; Source-free domain adaptation; Consistency regularization; Mutual alignment

向作者/读者索取更多资源

This paper focuses on the scenario of source-free domain adaptation (SFDA) and proposes a consistency regularization-based mutual alignment (CRMA) method. It randomly augments each target sample to increase sample diversity. It leverages the information maximization loss to improve the performance of mutual alignment. It aligns original samples and augmented samples to enhance the model's ability.
Unsupervised domain adaptation (UDA) is used to extend the model working on well-annotated source data to unlabeled target data. However, in practice, due to privacy and storage issues, we can only obtain the well-trained source model. In this paper, we focus on this scenario named source-free domain adaptation (SFDA). At present, nearest neighbors-based SFDA methods assume that the target features extracted by the source model can form clear clusters, and align samples with their neighbors. However, due to the domain discrepancy, adjacent features may belong to different categories. We propose consistency regularization-based mutual alignment (CRMA) to address this problem. Firstly, we randomly augment each target sample. Due to the domain discrepancy, it may lead to negative transfer if we align them directly. Therefore, secondly, we leverage the information maximization loss to all target and augmented samples, improving the performance of mutual alignment. Finally, we mutually align original samples and augmented samples. It improves the ability of the model and increases the variety of samples to alleviate the phenomenon that incorrectly aligning samples when aligning with neighbors. CRMA achieves state-of-the-art performance on 3 popular cross-domain benchmarks. Compared with the original method, CRMA has improvements of 0.4% up to 89.4%, 1.9% up to 72.2%, and 1.9% up to 85.9% on 3 datasets respectively. At the last, we verify the effectiveness of each part of CRMA through ablation experiments and use a series of experiments to analyze CRMA in detail.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据