While domain adaptation has been used to improve the performance of object detectors when the training and test data follow different distributions, previous work has mostly focused on two-stage detectors. This is because their use of region proposals makes it possible to perform local adaptation, which has been shown to significantly improve the adaptation effectiveness. Here, by contrast, we target single-stage architectures, which are better suited to resource-constrained detection than two-stage ones but do not provide region proposals. To nonetheless benefit from the strength of local adaptation, we introduce an attention mechanism that lets us identify the important regions on which adaptation should focus. Our method gradually adapts the features from global, image level to local, instance level. Our approach is generic and can be integrated into any Single-Shot Detector. We demonstrate this on standard benchmark datasets by applying it to both the single-shot detector (SSD) and a recent variant of the You Only Look Once detector (YOLOv5). Furthermore, for equivalent single-stage architectures, our method outperforms the state-of-the-art domain adaptation techniques even though they were designed for specific detectors.

虽然当训练和测试数据遵循不同的分布时，域适应已被用于提高对象检测器的性能，但以前的工作主要集中在两阶段检测器上。这是因为他们使用区域建议可以执行局部适应，这已被证明可以显着提高适应效率。相比之下，我们针对的是单阶段架构，它比两阶段架构更适合资源受限检测，但不提供区域建议。尽管如此，为了从局部适应的优势中受益，我们引入了一种注意力机制，让我们能够确定适应应该关注的重要区域。我们的方法逐渐适应从全局、图像级到局部、实例级的特征。我们的方法是通用的，可以集成到任何 Single-Shot Detector 中。我们通过将其应用于单次检测器 (SSD) 和 You Only Look Once 检测器 (YOLOv5) 的最新变体，在标准基准数据集上证明了这一点。此外，对于等效的单级架构，我们的方法优于最先进的域适应技术，即使它们是为特定检测器设计的。