This article studies a novel transfer learning problem termed distant domain transfer learning. Different from traditional transfer learning which assumes there is a close relation between source and target data, in this study, the objective is to execute an unseen and unrelated task based on a labelled data set training previously without any samples from intermediate domains. To this end, the authors propose deep unsupervised progressive learning (DUPL) framework and its upgraded version, end-to-end DUPL (eDUPL). eDUPL consists of two components, i.e. (i) translating the style of labelled images from irrelevant source domain to the target domain and (ii) learning a domain adaptation model with progressive learning for testing on the target domain. In comparison, eDUPL can integrate the two components of the framework seamlessly. In general, the proposed method is easy to be implemented and can be viewed as a strong convolutional baseline for distant domain adaptation task. Comprehensive experiments based on VeRi Vehicle, CUB-200-2011 Birds and Oxford5k Buildings data sets are conducted and the results indicate that the proposed method robustly achieves state-of-the-art performances compared with existing approaches, which demonstrates the effectiveness and superiority of the proposed algorithm.

中文翻译：

---

带有风格迁移的渐进式学习，用于远程域适应

本文研究了一个新的迁移学习问题，称为远程域迁移学习。与假设源数据和目标数据之间存在密切关系的传统迁移学习不同，在本研究中，目标是在没有来自中间域的任何样本的情况下，基于先前训练的标记数据集执行不可见且不相关的任务。为此，作者提出了深度无监督渐进式学习 (DUPL) 框架及其升级版本，端到端 DUPL (eDUPL)。eDUPL 由两个部分组成，即 (i) 将标记图像的风格从不相关的源域转换到目标域，以及 (ii) 通过渐进式学习学习域适应模型以在目标域上进行测试。相比之下，eDUPL 可以无缝集成框架的两个组件。一般来说，所提出的方法易于实现，可以看作是远域适应任务的强卷积基线。基于 Veri Vehicle、CUB-200-2011 Birds 和 Oxford5k Buildings 数据集进行了综合实验，结果表明，与现有方法相比，所提出的方法稳健地实现了最先进的性能，证明了该方法的有效性和优越性。提出的算法。