Semi-supervised object detection (SSOD) has made significant progress with the development of pseudo-label-based end-to-end methods. However, many of these methods face challenges due to class imbalance, which hinders the effectiveness of the pseudo-label generator. Furthermore, in the literature, it has been observed that low-quality pseudo-labels severely limit the performance of SSOD. In this paper, we examine the root causes of low-quality pseudo-labels and present novel learning mechanisms to improve the label generation quality. To cope with high false-negative and low precision rates, we introduce an adaptive thresholding mechanism that helps the proposed network to filter out optimal bounding boxes. We further introduce a Jitter-Bagging module to provide accurate information on localization to help refine the bounding boxes. Additionally, two new losses are introduced using the background and foreground scores predicted by the teacher and student networks to improvise the pseudo-label recall rate. Furthermore, our method applies strict supervision to the teacher network by feeding strong & weak augmented data to generate robust pseudo-labels so that it can detect small and complex objects. Finally, the extensive experiments show that the proposed network outperforms state-of-the-art methods on MS-COCO and Pascal VOC datasets and allows the baseline network to achieve 100% supervised performance with much less (i.e., 20%) labeled data.

本文提出了一种新的半监督目标检测方法，该方法在假标签生成器方面引入了新的学习机制以提高标签生成质量，并介绍了自适应阈值机制和 Jitter-Bagging 模块以提高边界框的精度和定位准确性，通过在教师网络上使用强调重和弱增强数据的严格监督来产生稳健的伪标签，在 MS-COCO 和 Pascal VOC 数据集上表现出色，且只需很少的标记数据即可实现 100％的监督表现。

重访类别不平衡对于端到端半监督目标检测的影响