Huang Wei, Shi Yilei, Xiong Zhitong, Wang Qi, Zhu Xiao Xiang
Chair of Data Science in Earth Observation, Technical University of Munich, Munich, 80333, Germany.
Chair of Remote Sensing Technology, Technical University of Munich, Munich, 80333, Germany.
ISPRS J Photogramm Remote Sens. 2023 Jan;195:192-203. doi: 10.1016/j.isprsjprs.2022.11.013.
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.
遥感（RS）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的人工标注数据。随着越来越多的RS图像可用，如何充分利用这些未标注数据成为一个紧迫的课题。半监督学习是一种直观的策略，它使用少量标注数据来指导大量未标注数据的自我训练。然而，由于不同数据集之间存在显著的域偏移，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）可以减少域偏移，并进一步将知识从一个全标注的RS场景数据集（源域）转移到一个有限标注的RS场景数据集（目标域），将是一个可行的解决方案。在本文中，我们提出了一种用于RS跨域场景分类的SSDA方法，称为双向样本-类别对齐（BSCA）。BSCA由两种对齐策略组成，无监督对齐（UA）和监督对齐（SA），两者都有助于减少域偏移。UA专注于减少跨域最大均值差异的距离，不需要类别标签。相比之下，SA旨在实现从源样本到相关目标类中心以及从目标样本到相关源类中心的分布对齐，并考虑到它们的类别。为了验证所提方法的有效性，我们在基于四个广泛使用的RS场景分类数据集构建的RS-SSDA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，与一些现有方法相比，我们的BSCA通过紧凑的特征表示和低熵分类边界实现了卓越的跨域分类性能。我们的代码将在https://github.com/hw2hwei/BSCA上提供。
