论文标题
一个简单的半监督学习框架，用于对象检测
A Simple Semi-Supervised Learning Framework for Object Detection
论文作者
论文摘要
半监督学习（SSL）有可能使用未标记的数据提高机器学习模型的预测性能。尽管最近取得了显着的进展，但SSL中的演示范围主要是在图像分类任务上。在本文中，我们提出了STAC，这是一个简单而有效的SSL框架，用于视觉对象检测以及数据增强策略。 STAC从未标记的图像中部署了局部对象的高度自信的伪标签，并通过强大的增强来实施一致性来更新模型。我们建议使用MS-Coco评估半监督对象检测的性能，并显示STAC对MS-COCO和VOC07的功效。在VOC07上，STAC将AP $^{0.5} $从$ 76.30 $提高到$ 79.08 $;在MS-Coco上，STAC通过仅使用5 \％标记的数据来实现24.38映射的数据效率$ 2 {\ times} $比使用10 \％标记的数据标记23.86 \％的监督基线的数据。该代码可在https://github.com/google-research/ssl_detection/上找到。
Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data. Although there has been remarkable recent progress, the scope of demonstration in SSL has mainly been on image classification tasks. In this paper, we propose STAC, a simple yet effective SSL framework for visual object detection along with a data augmentation strategy. STAC deploys highly confident pseudo labels of localized objects from an unlabeled image and updates the model by enforcing consistency via strong augmentations. We propose experimental protocols to evaluate the performance of semi-supervised object detection using MS-COCO and show the efficacy of STAC on both MS-COCO and VOC07. On VOC07, STAC improves the AP$^{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/.
