IEEE Trans Image Process. 2021;30:3793-3803. doi: 10.1109/TIP.2021.3065254. Epub 2021 Mar 23.
Multi-source domain adaptation (MSDA) aims to transfer knowledge from multi-source domains to one target domain. Inspired by single-source domain adaptation, existing methods solve MSDA by aligning the data distributions between the target domain and each source domain. However, aligning the target domain with the dissimilar source domain would harm the representation learning. To address the above issue, an intuitive motivation of MSDA is using the attention mechanism to enhance the positive effects of the similar domains, and suppress the negative effects of the dissimilar domains. Therefore, we propose Attention-Based Multi-Source Domain Adaptation (ABMSDA) by considering the domain correlations to alleviate the effects caused by dissimilar domains. To obtain the domain correlations between source and target domains, ABMSDA firstly trains a domain recognition model to calculate the probability that the target images belong to each source domain. Based on the domain correlations, Weighted Moment Distance (WMD) is proposed to pay more attention on the source domains with higher similarities. Furthermore, Attentive Classification Loss (ACL) is developed to constrain that the feature extractor can generate the alignment and discriminative visual representations. The evaluations on two benchmarks demonstrate the effectiveness of the proposed model, e.g., an average of 6.1% improvement on the challenging DomainNet dataset.
多源域自适应（MSDA）旨在将知识从多个源域转移到一个目标域。受单源域自适应的启发，现有的方法通过对齐目标域和每个源域之间的数据分布来解决 MSDA 问题。然而，将目标域与不相似的源域对齐会损害表示学习。为了解决上述问题，MSDA 的一个直观动机是使用注意力机制来增强相似域的积极影响，并抑制不相似域的负面影响。因此，我们通过考虑域相关性来提出基于注意力的多源域自适应（ABMSDA），以减轻不相似域带来的影响。为了获得源域和目标域之间的域相关性，ABMSDA 首先训练一个域识别模型来计算目标图像属于每个源域的概率。基于域相关性，提出了加权矩距离（WMD）来更多地关注具有更高相似性的源域。此外，还开发了注意分类损失（ACL）来约束特征提取器可以生成对齐和判别性的视觉表示。在两个基准上的评估表明了所提出模型的有效性，例如，在具有挑战性的 DomainNet 数据集上的平均提高了 6.1%。
