Due to the unique characteristics of remote sensing (RS) data, it is challenging to collect richer labeled samples for training the deep learning model compared with the natural image data. To solve this problem, recently, multisource-single-target (MS 2T^{2}\text{T} ) scenarios have started receiving significant attention in which the knowledge from multiple sources is integrated to transfer to a target domain with the assumption that label spaces of each source and target domain are the same. However, in real-world applications, it can be challenging to find a source domain that completely includes all classes of the target domain. Therefore, to cover all class information of the target domain, they often naïvely merge multiple sources into a complete single source. However, each source domain typically has a different data distribution; thus, the semantic information of each source domain can be damaged, leading to degrading the classification accuracy of the target domain. To address this problem, we propose a unified framework termed multiexpert collaboration for knowledge adaptation (MECKA) from various sources. MECKA includes two main processes: multiple-view generation and collaborative learning. Multiview learning plays an essential role in preserving the unique characteristics of each source domain. In contrast, collaborative learning is responsible for connecting these views that leverage complementary information from each other to perform on an unseen target domain robustly. Experimental results showed that the proposed method achieved the best classification accuracy on RS scene benchmark datasets on both complete and incomplete multisource unsupervised domain adaptation (UDA) tasks compared to benchmark methods.

中文翻译：

---

多位专家协作进行多遥感源知识适应


由于遥感（RS）数据的独特特征，与自然图像数据相比，收集更丰富的标记样本来训练深度学习模型具有挑战性。为了解决这个问题，最近，多源单目标（MS 2T^{2}\text{T} ）场景开始受到广泛关注，其中来自多个源的知识被集成以转移到目标域，假设：每个源域和目标域的标签空间是相同的。然而，在实际应用中，找到完全包含目标域所有类的源域可能具有挑战性。因此，为了覆盖目标域的所有类信息，他们经常天真地将多个源合并为一个完整的单个源。然而，每个源域通常具有不同的数据分布；因此，每个源域的语义信息可能会被损坏，导致目标域的分类精度下降。为了解决这个问题，我们提出了一个统一的框架，称为来自不同来源的知识适应多专家协作（MECKA）。 MECKA 包括两个主要过程：多视图生成和协作学习。多视图学习在保留每个源域的独特特征方面发挥着至关重要的作用。相比之下，协作学习负责连接这些视图，利用彼此的互补信息在看不见的目标领域上稳健地执行。实验结果表明，与基准方法相比，所提出的方法在完整和不完整的多源无监督域适应（UDA）任务上在 RS 场景基准数据集上实现了最佳分类精度。