Open compound domain adaptation (OCDA) is a domain adaptation setting, where target domain is modeled as a compound of multiple unknown homogeneous domains, which brings the advantage of improved generalization to unseen domains. In this work, we propose a principled meta-learning based approach to OCDA for semantic segmentation, MOCDA, by modeling the unlabeled target domain continuously. Our approach consists of four key steps. First, we cluster target domain into multiple sub-target domains by image styles, extracted in an unsupervised manner. Then, different sub-target domains are split into independent branches, for which batch normalization parameters are learnt to treat them independently. A meta-learner is thereafter deployed to learn to fuse sub-target domain-specific predictions, conditioned upon the style code. Meanwhile, we learn to online update the model by model-agnostic meta-learning (MAML) algorithm, thus to further improve generalization. We validate the benefits of our approach by extensive experiments on synthetic-to-real knowledge transfer benchmark datasets, where we achieve the state-of-the-art performance in both compound and open domains.
翻译:开放的复合域适应(OCDA)是一个领域适应设置,目标域是多个未知的同质域的复合体,具有改进普通化的优势。在这项工作中,我们提议对 OCDA 的语义分解(MOCDA)采用有原则的元学习方法,对无标签的目标域进行连续建模。我们的方法由四个关键步骤组成。首先,我们将目标域分组成多个次级目标域,通过图像样式,以不受监督的方式提取。然后,将不同次级目标域分成独立的分支,学习如何独立处理这些域。随后,我们部署一个元Learner,学习如何结合以样式代码为条件的子目标特定域预测。与此同时,我们学习通过模型-认知性元学习算法(MAML) 算法在线更新模型,从而进一步改进一般化。我们通过在综合到现实知识转移基准数据集方面的广泛实验,验证了我们的方法的效益。