Visual domain adaptation involves learning to classify images from a target visual domain using labels available in a different source domain. A range of prior work uses adversarial domain alignment to try and learn a domain invariant feature space, where a good source classifier can perform well on target data. This however, can lead to errors where class A features in the target domain get aligned to class B features in source. We show that in the presence of a few target labels, simple techniques like self-supervision (via rotation prediction) and consistency regularization can be effective without any adversarial alignment to learn a good target classifier. Our Pretraining and Consistency (PAC) approach, can achieve state of the art accuracy on this semi-supervised domain adaptation task, surpassing multiple adversarial domain alignment methods, across multiple datasets. Notably, it outperforms all recent approaches by 3-5% on the large and challenging DomainNet benchmark, showing the strength of these simple techniques in fixing errors made by adversarial alignment.

该研究展示出半监督领域自适应 (Semi-Supervised Domain Adaptation, SSDA) 可以在不需要特征对齐的情况下学习一个精度较高的目标分类器，使用自监督预训练和一致性正则化等简单技术可以实现良好的目标集群分离效果，超越多种对抗领域对齐方法在多个数据集上实现了卓越的目标精度。

预训练和一致性帮助简单半监督领域自适应