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。

领域自适应的图像到图像翻译