We propose a general framework for unsupervised domain adaptation, which
allows deep neural networks trained on a source domain to be tested on a
different target domain without requiring any training annotations in the
target domain. This is achieved by adding extra networks and losses that help
regularize the features extracted by the backbone encoder network. To this end
we propose the novel use of the recently proposed unpaired image-toimage
translation framework to constrain the features extracted by the encoder
network. Specifically, we require that the features extracted are able to
reconstruct the images in both domains. In addition we require that the
distribution of features extracted from images in the two domains are
indistinguishable. Many recent works can be seen as specific cases of our
general framework. We apply our method for domain adaptation between MNIST,
USPS, and SVHN datasets, and Amazon, Webcam and DSLR Office datasets in
classification tasks, and also between GTA5 and Cityscapes datasets for a
segmentation task. We demonstrate state of the art performance on each of these
datasets.

提出了一种无监督域适应的通用框架，利用添加额外的网络和损失函数，通过使用图像翻译框架和特征提取实现在无需目标域训练数据的情况下，测试源域训练的深度神经网络在不同的目标域上的能力，并在分类和分割任务上，应用于 MNIST、USPS、SVHN 和 Amazon、Webcam、DSLR Office 以及 GTA5 和 Cityscapes 数据集，取得了最先进的性能。