4.7 Article

A Two-Stage Adaptation Network (TSAN) for Remote Sensing Scene Classification in Single-Source-Mixed-Multiple-Target Domain Adaptation (S2M2T DA) Scenarios

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2021.3105302

关键词

Remote sensing; Annotations; Adaptation models; Sensors; Satellites; Earth; Data models; Adversarial learning; deep learning; domain adaptation (DA); mixed-multiple-target domain; remote sensing image classification; self-supervised learning

资金

  1. National Key Research and Development Program of China [2017YFA0604500]
  2. National Natural Science Foundation of China [U1839206]

向作者/读者索取更多资源

In this study, a new domain adaptation algorithm TSAN is proposed to address domain gap problems in scenarios with one source domain and mixed multiple target domains, achieving better results in remote sensing applications.
Over the past decade, domain adaptation (DA) algorithms have been proposed to address domain gap problems as they do not need any interpretation in the target domain. However, most existing efforts focus on scenarios with only one source domain and one target domain. In this article, we explore the scenario with one source domain and mixed multiple target domains for remote sensing applications and propose a new algorithm, named the two-stage adaptation network (TSAN). First, we utilize the adversarial learning approach to confuse the classifier to discriminate between the source domain and the whole mixed-multiple-target domain. Second, we adopt self-supervised learning to divide the mixed-multiple-target domain with automated generation of ``pseudo''-domain labels, which guides our network to learn intrinsic features of multiple target domains. Finally, these two steps are combined as an iterative procedure. We integrate a test dataset that includes five remote sensing datasets and ten classes. Our method achieves an average accuracy of 63.25% and 73.68% with two typical backbones, considerably outperforming other DA methods with an average accuracy improvement of 4.84%-20.19% and 9.06%-17.04%, respectively. Furthermore, we identify the negative transfer effect in existing mainstream DA methods in remote sensing image classification with multiple different domains.

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