4.7 Article

SENECA: Change detection in optical imagery using Siamese networks with Active-Transfer Learning

期刊

EXPERT SYSTEMS WITH APPLICATIONS
卷 214, 期 -, 页码 -

出版社

PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2022.119123

关键词

Active learning; Transfer learning; Siamese network; Change detection; Sentinel-2 data

向作者/读者索取更多资源

This paper proposes a method called SENECA, which is based on a CD Siamese network and uses transfer learning and active learning to handle the constraint of limited supervision in order to learn an accurate CD model with limited labelled data. The experimental results demonstrate the significant benefits of the proposed method in improving the accuracy of CD decisions.
Change Detection (CD) aims to distinguish surface changes based on bi-temporal remote sensing images. In recent years, deep neural models have made a breakthrough in CD processes. However, training a deep neural model requires a large volume of labelled training samples that are time-consuming and labour-intensive to acquire. With the aim of learning an accurate CD model with limited labelled data, we propose SENECA: a method based on a CD Siamese network, which takes advantage of both Transfer Learning (TL) and Active Learning (AL) to handle the constraint of limited supervision. More precisely, we jointly use AL and TL to adapt a CD model trained on a labelled source domain to a (related) target domain featured by restricted access to labelled data. We report results from an experimental evaluation involving five pairs of images acquired via Sentinel-2 satellites between 2015 and 2018 in various locations picked all over Asia and USA. The results show the beneficial effects of the proposed AL and TL strategies on the accuracy of the decisions made by the CD Siamese network and depict the merit of the proposed approach over competing CD baselines.

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