Object detectors do not work well when domains largely differ between training and testing data. To overcome this domain gap in object detection without requiring expensive annotations, we consider two problem settings: semi-supervised domain generalizable object detection (SS-DGOD) and weakly-supervised DGOD (WS-DGOD). In contrast to the conventional domain generalization for object detection that requires labeled data from multiple domains, SS-DGOD and WS-DGOD require labeled data only from one domain and unlabeled or weakly-labeled data from multiple domains for training. In this paper, we show that object detectors can be effectively trained on the two settings with the same Mean Teacher learning framework, where a student network is trained with pseudo-labels output from a teacher on the unlabeled or weakly-labeled data. We provide novel interpretations of why the Mean Teacher learning framework works well on the two settings in terms of the relationships between the generalization gap and flat minima in parameter space. On the basis of the interpretations, we also show that incorporating a simple regularization method into the Mean Teacher learning framework leads to flatter minima. The experimental results demonstrate that the regularization leads to flatter minima and boosts the performance of the detectors trained with the Mean Teacher learning framework on the two settings.

翻译：当训练数据与测试数据之间存在显著领域差异时，目标检测器的性能会大幅下降。为在不依赖昂贵标注的情况下克服目标检测中的领域差异，我们提出两种问题设定：半监督领域泛化目标检测（SS-DGOD）与弱监督领域泛化目标检测（WS-DGOD）。相较于传统需要多领域标注数据的目标检测领域泛化方法，SS-DGOD与WS-DGOD仅需单一领域的标注数据，以及来自多个领域的未标注或弱标注数据进行训练。本文证明，通过采用统一的均值教师学习框架，可在两种设定下有效训练目标检测器：该框架利用教师网络对未标注/弱标注数据生成的伪标签来训练学生网络。我们从泛化间隙与参数空间平坦最小值之间关系的角度，对均值教师框架在两种设定中表现优异的原因提出了创新性理论阐释。基于此理论分析，我们进一步证明在均值教师框架中引入简单的正则化方法能够获得更平坦的极小值。实验结果表明，该正则化方法确实能产生更平坦的极小值，并显著提升了均值教师框架在两种设定下所训练检测器的性能。