首页 文献索引 SCI期刊 AI助手
登录 注册
首页 正文

ISPRS journal of photogrammetry and remote sensing : official publication of the International Society for Photogrammetry and Remote Sensing (ISPRS). 2023 Jan:195:192-203. doi: 10.1016/j.isprsjprs.2022.11.013 Q110.62024

Semi-supervised bidirectional alignment for Remote Sensing cross-domain scene classification

半监督双向对齐的遥感跨领域场景分类方法 翻译改进

Wei Huang  1, Yilei Shi  2, Zhitong Xiong  1, Qi Wang  3, Xiao Xiang Zhu  1

作者单位 +展开

作者单位

  • 1 Chair of Data Science in Earth Observation, Technical University of Munich, Munich, 80333, Germany.
  • 2 Chair of Remote Sensing Technology, Technical University of Munich, Munich, 80333, Germany.
  • 3 School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi'an, 710072, China.
  • DOI: 10.1016/j.isprsjprs.2022.11.013 PMID: 36726963

    摘要 中英对照阅读

    Remote sensing (RS) image scene classification has obtained increasing attention for its broad application prospects. Conventional fully-supervised approaches usually require a large amount of manually-labeled data. As more and more RS images becoming available, how to make full use of these unlabeled data is becoming an urgent topic. Semi-supervised learning, which uses a few labeled data to guide the self-training of numerous unlabeled data, is an intuitive strategy. However, it is hard to apply it to cross-dataset (i.e., cross-domain) scene classification due to the significant domain shift among different datasets. To this end, semi-supervised domain adaptation (SSDA), which can reduce the domain shift and further transfer knowledge from a fully-labeled RS scene dataset (source domain) to a limited-labeled RS scene dataset (target domain), would be a feasible solution. In this paper, we propose an SSDA method termed bidirectional sample-class alignment (BSCA) for RS cross-domain scene classification. BSCA consists of two alignment strategies, unsupervised alignment (UA) and supervised alignment (SA), both of which can contribute to decreasing domain shift. UA concentrates on reducing the distance of maximum mean discrepancy across domains, with no demand for class labels. In contrast, SA aims to achieve the distribution alignment both from source samples to the associate target class centers and from target samples to the associate source class centers, with awareness of their classes. To validate the effectiveness of the proposed method, extensive ablation, comparison, and visualization experiments are conducted on an RS-SSDA benchmark built upon four widely-used RS scene classification datasets. Experimental results indicate that in comparison with some state-of-the-art methods, our BSCA achieves the superior cross-domain classification performance with compact feature representation and low-entropy classification boundary. Our code will be available at https://github.com/hw2hwei/BSCA.

    Keywords: Bidirectional sample-class alignment; Cross-domain classification; Remote sensing; Semi-supervised domain adaptation.

    Keywords:remote sensing; semi-supervised learning

    遥感图像场景分类因其广阔的应用前景而受到越来越多的关注。传统的全监督方法通常需要大量手动标记的数据。随着越来越多的遥感图像可用,如何充分利用这些未标记的数据正成为一个迫切的课题。半监督学习是一种直观的策略,它使用一些标记数据来指导大量未标记数据的自我训练。然而,由于不同数据集之间存在显著的域偏移,因此很难将其应用于跨数据集(即跨域)场景分类。为此,半监督域自适应(SSDA)是一种可行的解决方案,它可以减少域偏移,并进一步将知识从完全标记的RS场景数据集(源域)转移到有限标记的RS现场数据集(目标域)。本文提出了一种用于RS跨域场景分类的双向样本类对齐(BSCA)SSDA方法。BSCA由两种对齐策略组成,无监督对齐(UA)和监督对齐(SA),这两种策略都有助于减少域偏移。UA专注于减少跨域最大平均差异的距离,而不需要类标签。相比之下,SA旨在实现从源样本到关联目标类中心以及从目标样本到关联源类中心的分布对齐,并意识到它们的类。为了验证所提出方法的有效性,在基于四个广泛使用的RS场景分类数据集的RS-SDA基准上进行了广泛的消融、比较和可视化实验。实验结果表明,与一些最先进的方法相比,我们的BSCA以紧凑的特征表示和低熵分类边界实现了优越的跨域分类性能。我们的代码将在https://github.com/hw2hwei/BSCA.关键词:双向样本类对齐;跨域分类;遥感;半监督域自适应。©2022作者。

    关键词:遥感; 跨领域场景分类; 半监督学习

    翻译效果不满意? 用Ai改进或 寻求AI助手帮助 ,对摘要进行重点提炼
    Copyright © ISPRS journal of photogrammetry and remote sensing : official publication of the International Society for Photogrammetry and Remote Sensing (ISPRS). 中文内容为AI机器翻译,仅供参考!

    相关内容

    期刊名:Isprs journal of photogrammetry and remote sensing

    缩写:ISPRS J PHOTOGRAMM

    ISSN:0924-2716

    e-ISSN:

    IF/分区:10.6/Q1

    文章目录 更多期刊信息

    全文链接
    引文链接
    复制
    已复制!
    推荐内容
    Semi-supervised bidirectional alignment for Remote Sensing cross-domain scene classification