Domain adaptive object detection (DAOD) assumes that both labeled source data and unlabeled target data are available for training, but this assumption does not always hold in real-world scenarios. Thus, source-free DAOD is proposed to adapt the source-trained detectors to target domains with only unlabeled target data. Existing source-free DAOD methods typically utilize pseudo labeling, where the performance heavily relies on the selection of confidence threshold. However, most prior works adopt a single fixed threshold for all classes to generate pseudo labels, which ignore the imbalanced class distribution, resulting in biased pseudo labels. In this work, we propose a refined pseudo labeling framework for source-free DAOD. First, to generate unbiased pseudo labels, we present a category-aware adaptive threshold estimation module, which adaptively provides the appropriate threshold for each category. Second, to alleviate incorrect box regression, a localization-aware pseudo label assignment strategy is introduced to divide labels into certain and uncertain ones and optimize them separately. Finally, extensive experiments on four adaptation tasks demonstrate the effectiveness of our method.

翻译：域自适应目标检测（DAOD）假设训练过程中同时存在带标签的源域数据和无标签的目标域数据，但在实际场景中这一假设并不总是成立。因此，无源域自适应目标检测被提出，旨在仅利用无标签目标域数据使源域训练好的检测器适应目标域。现有无源域DAOD方法通常采用伪标签技术，其性能严重依赖于置信度阈值的选取。然而，大多数先前工作对伪标签生成采用所有类别统一的固定阈值，忽略了不平衡的类别分布，导致伪标签存在偏差。本文提出了一种面向无源域DAOD的精炼伪标签框架。首先，为生成无偏伪标签，我们提出类别感知的自适应阈值估计模块，该模块能够为每个类别自适应地提供合适阈值。其次，为缓解不准确的边界框回归，引入了一种定位感知的伪标签分配策略，将标签分为确定标签和不确定标签并分别进行优化。最后，在四个自适应任务上的大量实验验证了本方法的有效性。