Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data. Although there has been remarkable recent progress, the scope of demonstration in SSL has mainly been on image classification tasks. In this paper, we propose STAC, a simple yet effective SSL framework for visual object detection along with a data augmentation strategy. STAC deploys highly confident pseudo labels of localized objects from an unlabeled image and updates the model by enforcing consistency via strong augmentations. We propose experimental protocols to evaluate the performance of semi-supervised object detection using MS-COCO and show the efficacy of STAC on both MS-COCO and VOC07. On VOC07, STAC improves the AP$^{0.5}$ from $76.30$ to $79.08$; on MS-COCO, STAC demonstrates $2{\times}$ higher data efficiency by achieving 24.38 mAP using only 5\% labeled data than supervised baseline that marks 23.86\% using 10\% labeled data. The code is available at https://github.com/google-research/ssl_detection/.

翻译：虽然最近取得了显著进展,但SSL的示范范围主要在于图像分类任务。在本文件中,我们提议STAC,这是用于视觉物体探测的简单而有效的SSL框架,同时提出了数据增强战略。STAC从未贴标签的图像中安装了高度自信的本地物体假标签,并通过强力增强来实施一致性,对模型进行更新。我们提出实验协议,以评价使用MS-COCO进行半监控物体探测的性能,并展示STAC对MS-CO和VOC07的功效。关于VOC07,STAC将AP$$+76.30美元提高到79.08美元;关于MS-CO,STAC通过使用比监控基线23.86 ⁇ 10 ⁇ 的标签数据,仅使用5 ⁇ 的标签数据实现24.38 mAP,显示数据效率更高2美元。该代码见https://github.com/google-research/sl_dection/ 。