论文标题
MDALU：多源域的适应和与部分数据集的标签统一
mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets
论文作者
论文摘要
对象识别的一个挑战是将新域，更多类和/或新模式概括。这需要方法来组合和重复可能属于不同域，具有部分注释和/或具有不同数据模式的现有数据集。本文将其作为多源域的适应性和标签统一问题，并提出了一种新方法。我们的方法包括部分监督的适应阶段和一个完全监督的适应阶段。在前者中，部分知识将从多个源域转移到目标域并在其中融合。通过三个新的模块减轻了无与伦比的标签空间之间的负转移：域的注意力，不确定性最大化和注意力引导的对抗比对。在后者中，在具有伪标签的标签完成过程之后，知识在统一标签空间中转移。对三个不同任务的广泛实验 - 图像分类，2D语义图像分割和关节2d -3d语义分割 - 表明我们的方法的表现明显优于所有竞争方法。
One challenge of object recognition is to generalize to new domains, to more classes and/or to new modalities. This necessitates methods to combine and reuse existing datasets that may belong to different domains, have partial annotations, and/or have different data modalities. This paper formulates this as a multi-source domain adaptation and label unification problem, and proposes a novel method for it. Our method consists of a partially-supervised adaptation stage and a fully-supervised adaptation stage. In the former, partial knowledge is transferred from multiple source domains to the target domain and fused therein. Negative transfer between unmatching label spaces is mitigated via three new modules: domain attention, uncertainty maximization and attention-guided adversarial alignment. In the latter, knowledge is transferred in the unified label space after a label completion process with pseudo-labels. Extensive experiments on three different tasks - image classification, 2D semantic image segmentation, and joint 2D-3D semantic segmentation - show that our method outperforms all competing methods significantly.
