Semi-Supervised Object Detection (SSOD) has achieved resounding success by leveraging unlabeled data to improve detection performance. However, in Open Scene Semi-Supervised Object Detection (O-SSOD), unlabeled data may contains unknown objects not observed in the labeled data, which will increase uncertainty in the model's predictions for known objects. It is detrimental to the current methods that mainly rely on self-training, as more uncertainty leads to the lower localization and classification precision of pseudo labels. To this end, we propose Credible Teacher, an end-to-end framework. Credible Teacher adopts an interactive teaching mechanism using flexible labels to prevent uncertain pseudo labels from misleading the model and gradually reduces its uncertainty through the guidance of other credible pseudo labels. Empirical results have demonstrated our method effectively restrains the adverse effect caused by O-SSOD and significantly outperforms existing counterparts.

翻译：半监督目标检测（SSOD）通过利用未标注数据提升检测性能取得了显著成功。然而，在开放场景半监督目标检测（O-SSOD）中，未标注数据可能包含标注数据中未观测到的未知物体，这将增加模型对已知物体预测的不确定性。这对当前主要依赖自训练的方法极为不利，因为更高的不确定性会导致伪标签的定位与分类精度降低。为此，我们提出了一种端到端框架——可信教师。该框架采用基于灵活标签的交互式教学机制，防止不确定的伪标签误导模型，并通过其他可信伪标签的引导逐步降低其不确定性。实验结果表明，我们的方法有效抑制了O-SSOD带来的负面影响，并显著优于现有方法。