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:半监督天体探测(GREP)是计算机视野的研究热点,这可以大大降低昂贵的捆绑框说明的要求。尽管取得了巨大成功,但目前的进展主要集中于两个阶段的检测网络,如ApperRCNN, 而一阶段探测器的研究往往被忽视。在本文中,我们的重点是为先进和流行的一阶段探测网络YOLOv5. 进行半监督的学习。与Georger-RCNN相比,YOLOv5 的实施更为复杂,YOLOv5 使用的各种认证技术也可以降低裁军特别联大的效益。除了这项挑战外,我们还在一阶段裁军特别峰会上发现了两个关键问题,分别是低质量的伪标签和多任务优化。为了解决这些问题,我们建议建立一个名为“One Teacher”的新教师学习食谱,有两个创新设计,即多视图 Pseudodo-label Refilment(MPR), 以及大规模Secouped Oppilation (DSOVO) 的升级方法,我们也可以通过Oral-GILEGIL 改进和OILT任务的升级。