Transfer learning leverages knowledge from other domains and has been successful in many applications. Transfer learning methods rely on the overall similarity of the source and target domains. However, in some cases, it is impossible to provide an overall similar source domain, and only some source domains with similar local features can be provided. Can transfer learning be achieved? In this regard, we propose a multi-source adversarial transfer learning method based on local feature similarity to the source domain to handle transfer scenarios where the source and target domains have only local similarities. This method extracts transferable local features between a single source domain and the target domain through a sub-network. Specifically, the feature extractor of the sub-network is induced by the domain discriminator to learn transferable knowledge between the source domain and the target domain. The extracted features are then weighted by an attention module to suppress non-transferable local features while enhancing transferable local features. In order to ensure that the data from the target domain in different sub-networks in the same batch is exactly the same, we designed a multi-source domain independent strategy to provide the possibility for later local feature fusion to complete the key features required. In order to verify the effectiveness of the method, we made the dataset "Local Carvana Image Masking Dataset". Applying the proposed method to the image segmentation task of the proposed dataset achieves better transfer performance than other multi-source transfer learning methods. It is shown that the designed transfer learning method is feasible for transfer scenarios where the source and target domains have only local similarities.

翻译：迁移学习利用其他领域的知识，并在许多应用中取得了成功。现有迁移学习方法依赖于源域与目标域的整体相似性。然而，在某些情况下，无法提供整体相似的源域，而只能提供一些具有相似局部特征的源域。这种情况下能否实现迁移学习？针对此问题，我们提出了一种基于源域局部特征相似性的多源对抗迁移学习方法，以处理源域与目标域仅具有局部相似性的迁移场景。该方法通过子网络提取单个源域与目标域之间的可迁移局部特征。具体而言，子网络的特征提取器在域判别器的诱导下学习源域与目标域之间的可迁移知识。随后，通过注意力模块对提取的特征进行加权，抑制不可迁移的局部特征，同时增强可迁移的局部特征。为确保同一批次中不同子网络的目标域数据完全相同，我们设计了一种多源域独立策略，为后续局部特征融合以补全所需关键特征提供了可能性。为验证方法的有效性，我们构建了数据集“Local Carvana Image Masking Dataset”。将所提方法应用于该数据集的图像分割任务，获得了优于其他多源迁移学习方法的迁移性能。研究表明，所设计的迁移学习方法对于源域与目标域仅具有局部相似性的迁移场景是可行的。