论文标题
通用域自适应对象检测器
Universal Domain Adaptive Object Detector
论文作者
论文摘要
通用域自适应对象检测（UNIDAOD）比域自适应对象检测（DAOD）更具挑战性，因为源域的标签空间可能与目标的标签空间不相同，并且通用场景中对象的规模可能会大大变化（即类别移位和量表移动）。为此，我们提出了US-DAF，即使用多标签学习的US-DAF，即具有多个标记的rcnn自适应域，以减少训练期间的负转移效应，同时最大化可传递性以及在各种规模下的两个领域的可区分性。具体而言，我们的方法由两个模块实现：1）我们通过设计滤波器机制模块来克服由类别移动引起的负转移来促进普通类的特征对齐，并抑制私人类的干扰。 2）我们通过引入一个新的多标签尺度感知适配器来在对象检测中填充比例感知适应的空白，以在两个域的相应刻度之间执行单个对齐。实验表明，US-DAF在三种情况下（即开放式，部分集和封闭设置）实现最新结果，并在基准数据集clipart1k和水彩颜色的基准数据集对相对相对改善中产生7.1％和5.9％的相对改善。
Universal domain adaptive object detection (UniDAOD)is more challenging than domain adaptive object detection (DAOD) since the label space of the source domain may not be the same as that of the target and the scale of objects in the universal scenarios can vary dramatically (i.e, category shift and scale shift). To this end, we propose US-DAF, namely Universal Scale-Aware Domain Adaptive Faster RCNN with Multi-Label Learning, to reduce the negative transfer effect during training while maximizing transferability as well as discriminability in both domains under a variety of scales. Specifically, our method is implemented by two modules: 1) We facilitate the feature alignment of common classes and suppress the interference of private classes by designing a Filter Mechanism module to overcome the negative transfer caused by category shift. 2) We fill the blank of scale-aware adaptation in object detection by introducing a new Multi-Label Scale-Aware Adapter to perform individual alignment between the corresponding scale for two domains. Experiments show that US-DAF achieves state-of-the-art results on three scenarios (i.e, Open-Set, Partial-Set, and Closed-Set) and yields 7.1% and 5.9% relative improvement on benchmark datasets Clipart1k and Watercolor in particular.
