论文标题
类新型域的适应性
Class-Incremental Domain Adaptation
论文作者
论文摘要
我们引入了一个实际领域适应性（DA）范式，称为类新型域适应性（CIDA）。现有的DA方法可以解决域转移，但不适合学习新颖的目标域类。同时，班级信息（CI）方法使得在没有源培训数据的情况下可以学习新课程，但在域换档下失败而没有标记的监督。在这项工作中，我们有效地确定了CIDA范式中这些方法的局限性。由理论和经验观察的促进，我们提出了一种受典型网络启发的有效方法，即使在域偏移下，也可以将目标样本分类为共享和新颖的（一声）目标类别。与CIDA范式中的DA和CI方法相比，我们的方法可以产生出色的性能。
We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA). Existing DA methods tackle domain-shift but are unsuitable for learning novel target-domain classes. Meanwhile, class-incremental (CI) methods enable learning of new classes in absence of source training data but fail under a domain-shift without labeled supervision. In this work, we effectively identify the limitations of these approaches in the CIDA paradigm. Motivated by theoretical and empirical observations, we propose an effective method, inspired by prototypical networks, that enables classification of target samples into both shared and novel (one-shot) target classes, even under a domain-shift. Our approach yields superior performance as compared to both DA and CI methods in the CIDA paradigm.
