Pseudo-Labeling has emerged as a simple yet effective technique for semi-supervised object detection (SSOD). However, the inevitable noise problem in pseudo-labels significantly degrades the performance of SSOD methods. Recent advances effectively alleviate the classification noise in SSOD, while the localization noise which is a non-negligible part of SSOD is not well-addressed. In this paper, we analyse the localization noise from the generation and learning phases, and propose two strategies, namely pseudo-label correction and noise-unaware learning. For pseudo-label correction, we introduce a multi-round refining method and a multi-vote weighting method. The former iteratively refines the pseudo boxes to improve the stability of predictions, while the latter smoothly self-corrects pseudo boxes by weighing the scores of surrounding jittered boxes. For noise-unaware learning, we introduce a loss weight function that is negatively correlated with the Intersection over Union (IoU) in the regression task, which pulls the predicted boxes closer to the object and improves localization accuracy. Our proposed method, Pseudo-label Correction and Learning (PCL), is extensively evaluated on the MS COCO and PASCAL VOC benchmarks. On MS COCO, PCL outperforms the supervised baseline by 12.16, 12.11, and 9.57 mAP and the recent SOTA (SoftTeacher) by 3.90, 2.54, and 2.43 mAP under 1\%, 5\%, and 10\% labeling ratios, respectively. On PASCAL VOC, PCL improves the supervised baseline by 5.64 mAP and the recent SOTA (Unbiased Teacherv2) by 1.04 mAP on AP$^{50}$.

翻译：伪标签技术已成为半监督目标检测中一种简单而有效的方法。然而，伪标签中不可避免的噪声问题显著降低了半监督目标检测方法的性能。近期研究有效缓解了半监督目标检测中的分类噪声，但作为其中不可忽视部分的定位噪声仍未得到良好解决。本文从生成与学习两个阶段分析定位噪声，并提出两种策略：伪标签校正与噪声无知学习。在伪标签校正方面，我们引入多轮精炼方法与多投票加权方法。前者通过迭代优化伪标签框提高预测稳定性，后者则通过加权周围抖动框的分数平滑地自校正伪标签框。对于噪声无知学习，我们提出一种损失权重函数，该函数与回归任务中的交并比呈负相关，从而将预测框拉近目标并提升定位精度。所提方法PCL（伪标签校正与学习）在MS COCO和PASCAL VOC基准上进行了广泛评估。在MS COCO上，PCL在1%、5%和10%标注比例下分别以12.16、12.11和9.57 mAP超越监督基线，并以3.90、2.54和2.43 mAP超越最新技术SoftTeacher。在PASCAL VOC上，PCL在AP$^{50}$指标上以5.64 mAP提升监督基线，并以1.04 mAP超越最新技术Unbiased Teacherv2。