This paper studies a new, practical but challenging problem, called Class-Incremental Unsupervised Domain Adaptation (CI-UDA), where the labeled source domain contains all classes, but the classes in the unlabeled target domain increase sequentially. This problem is challenging due to two difficulties. First, source and target label sets are inconsistent at each time step, which makes it difficult to conduct accurate domain alignment. Second, previous target classes are unavailable in the current step, resulting in the forgetting of previous knowledge. To address this problem, we propose a novel Prototype-guided Continual Adaptation (ProCA) method, consisting of two solution strategies. 1) Label prototype identification: we identify target label prototypes by detecting shared classes with cumulative prediction probabilities of target samples. 2) Prototype-based alignment and replay: based on the identified label prototypes, we align both domains and enforce the model to retain previous knowledge. With these two strategies, ProCA is able to adapt the source model to a class-incremental unlabeled target domain effectively. Extensive experiments demonstrate the effectiveness and superiority of ProCA in resolving CI-UDA. The source code is available at https://github.com/Hongbin98/ProCA.git
翻译:本文研究了一个新的、实际但具有挑战性的问题,即所谓的“等级强化的、不受监督的域适应”(CI-UDA),标签源域包含所有类别,但未贴标签目标域的类别依次增加。由于两个困难,这一问题具有挑战性。首先,源和目标标签组在每一步都不一致,因此难以进行准确的域对齐。第二,在目前步骤中,没有前几个目标类,导致忘记先前的知识。为了解决这一问题,我们提议了一种新型的原型指导持续适应(ProCA)方法,包括两个解决方案战略。 1) Label原型识别:我们通过用累积预测指标样本概率探测共享类确定标签原型。2)基于原型的原型调整和重播:根据已查明的标签原型,我们调整了两个领域,并强制执行模型以保留先前的知识。根据这两个战略,ProCAA能够将源模型改制成一个等级的、未贴标签的目标域。广泛实验展示了Pro-HUDA/CA。