Semi-Supervised Object Detection (SSOD) has been successful in improving the performance of both R-CNN series and anchor-free detectors. However, one-stage anchor-based detectors lack the structure to generate high-quality or flexible pseudo labels, leading to serious inconsistency problems in SSOD, such as YOLOv5. In this paper, we propose the Efficient Teacher framework for scalable and effective one-stage anchor-based SSOD training, consisting of Dense Detector, Pseudo Label Assigner, and Epoch Adaptor. Dense Detector is a baseline model that extends RetinaNet with dense sampling techniques inspired by YOLOv5. The Efficient Teacher framework introduces a novel pseudo label assignment mechanism, named Pseudo Label Assigner, which makes more refined use of pseudo labels from Dense Detector. Epoch Adaptor is a method that enables a stable and efficient end-to-end semi-supervised training schedule for Dense Detector. The Pseudo Label Assigner prevents the occurrence of bias caused by a large number of low-quality pseudo labels that may interfere with the Dense Detector during the student-teacher mutual learning mechanism, and the Epoch Adaptor utilizes domain and distribution adaptation to allow Dense Detector to learn globally distributed consistent features, making the training independent of the proportion of labeled data. Our experiments show that the Efficient Teacher framework achieves state-of-the-art results on VOC, COCO-standard, and COCO-additional using fewer FLOPs than previous methods. To the best of our knowledge, this is the first attempt to apply Semi-Supervised Object Detection to YOLOv5.

翻译：半监督目标检测（SSOD）在提升R-CNN系列与无锚框检测器性能方面已取得成功。然而，单阶段锚框类检测器因缺乏生成高质量或灵活伪标签的结构，导致SSOD中存在严重不一致性问题（如YOLOv5）。本文提出高效教师框架，用于实现可扩展且高效的单阶段锚框类SSOD训练，该框架包含密集检测器、伪标签分配器和时期适配器三个模块。密集检测器是一种基线模型，它借鉴YOLOv5的密集采样技术扩展了RetinaNet。高效教师框架引入新型伪标签分配机制——伪标签分配器，可对密集检测器生成的伪标签进行更精细化利用。时期适配器则为密集检测器提供稳定高效的全半监督端到端训练方案。伪标签分配器可避免师生互学机制中大量低质量伪标签对密集检测器产生干扰偏差；时期适配器通过域适应与分布自适应使密集检测器学习全局分布一致性特征，从而实现训练过程与标注数据比例无关。实验表明，高效教师框架在VOC、COCO标准集和COCO扩展集上均以更少FLOPs达到当前最优性能。据我们所知，这是首次将半监督目标检测应用于YOLOv5。