Semi-supervised object detection (SSOD) is a research hot spot in computer vision, which can greatly reduce the requirement for expensive bounding-box annotations. Despite great success, existing progress mainly focuses on two-stage detection networks like FasterRCNN, while the research on one-stage detectors is often ignored. In this paper, we focus on the semi-supervised learning for the advanced and popular one-stage detection network YOLOv5. Compared with Faster-RCNN, the implementation of YOLOv5 is much more complex, and the various training techniques used in YOLOv5 can also reduce the benefit of SSOD. In addition to this challenge, we also reveal two key issues in one-stage SSOD, which are low-quality pseudo-labeling and multi-task optimization conflict, respectively. To address these issues, we propose a novel teacher-student learning recipe called OneTeacher with two innovative designs, namely Multi-view Pseudo-label Refinement (MPR) and Decoupled Semi-supervised Optimization (DSO). In particular, MPR improves the quality of pseudo-labels via augmented-view refinement and global-view filtering, and DSO handles the joint optimization conflicts via structure tweaks and task-specific pseudo-labeling. In addition, we also carefully revise the implementation of YOLOv5 to maximize the benefits of SSOD, which is also shared with the existing SSOD methods for fair comparison. To validate OneTeacher, we conduct extensive experiments on COCO and Pascal VOC. The extensive experiments show that OneTeacher can not only achieve superior performance than the compared methods, e.g., 15.0% relative AP gains over Unbiased Teacher, but also well handle the key issues in one-stage SSOD. Our source code is available at: https://github.com/luogen1996/OneTeacher.

翻译：半监督目标检测（SSOD）是计算机视觉领域的研究热点，其能显著降低对昂贵边界框标注的需求。尽管已取得巨大成功，现有进展主要集中于Faster R-CNN等两阶段检测网络，而对单阶段检测器的研究常被忽视。本文聚焦于先进且流行的单阶段检测网络YOLOv5的半监督学习。相较于Faster R-CNN，YOLOv5的实现更为复杂，其使用的多种训练技术可能削弱SSOD的收益。除这一挑战外，我们还揭示了单阶段SSOD中的两个关键问题：低质量伪标签与多任务优化冲突。为解决这些问题，我们提出一种新颖的师生学习方案OneTeacher，包含两项创新设计：多视角伪标签细化（MPR）与解耦半监督优化（DSO）。具体而言，MPR通过增强视图细化与全局视图过滤提升伪标签质量，DSO通过结构调整与任务特定伪标签处理联合优化冲突。此外，我们审慎修订了YOLOv5的实现以最大化SSOD收益，该实现亦与现有SSOD方法共享以实现公平对比。为验证OneTeacher，我们在COCO与Pascal VOC上进行了大量实验。广泛实验表明，OneTeacher不仅相较对比方法取得更优性能（例如相较于Unbiased Teacher实现15.0%的相对AP提升），且有效解决了单阶段SSOD的关键问题。我们的源代码已开源：https://github.com/luogen1996/OneTeacher。