Existing domain adaptation methods assume that domain discrepancies are caused by a few discrete attributes and variations, e.g., art, real, painting, quickdraw, etc. We argue that this is not realistic as it is implausible to define the real-world datasets using a few discrete attributes. Therefore, we propose to investigate a new problem namely the Continuous Domain Adaptation (CDA) through the lens where infinite domains are formed by continuously varying attributes. Leveraging knowledge of two labeled source domains and several observed unlabeled target domains data, the objective of CDA is to learn a generalized model for whole data distribution with the continuous attribute. Besides the contributions of formulating a new problem, we also propose a novel approach as a strong CDA baseline. To be specific, firstly we propose a novel alternating training strategy to reduce discrepancies among multiple domains meanwhile generalize to unseen target domains. Secondly, we propose a continuity constraint when estimating the cross-domain divergence measurement. Finally, to decouple the discrepancy from the mini-batch size, we design a domain-specific queue to maintain the global view of the source domain that further boosts the adaptation performances. Our method is proven to achieve the state-of-the-art in CDA problem using extensive experiments. The code is available at https://github.com/SPIresearch/CDA.
翻译:现有领域适应方法假定,领域差异是由少数离散属性和变异(如艺术、真实、绘画、快速绘制等)导致的。我们争辩说,这不现实,因为用一些离散属性定义真实世界数据集是不可行的,因此,我们提议调查一个新问题,即通过透镜持续域的无限域由连续不同属性形成,通过透镜持续域的无限域构成,持续域适应(CDA),利用两个标签源域和几个观察到的未标记目标域数据的知识,CDA的目标是学习一个具有连续属性的全数据分布通用模型。除了提出新问题的贡献外,我们还提议以新的方法作为CDA的强大基线。具体地说,我们建议采用新的交替培训战略,以减少多个域之间的差异,同时向看不见的目标域推广。第二,我们提出在估算交叉域差异测量时的连续性限制。最后,为了消除与微批量数据大小的差异,我们设计一个特定域排队以保持源域的全局观点,从而进一步提升CD/CD的适应性能。