arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.09480cs.CVcs.LG
收藏

半监督目标检测的无偏教师

Unbiased Teacher for Semi-Supervised Object Detection

Georgia Tech(佐治亚理工学院);Facebook Inc.(脸书公司)

Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, Peter Vajda

摘要:

半监督学习,即,训练网络的标记和未标记的数据,最近取得了重大进展。然而,现有的工作主要集中在图像分类任务和忽视目标检测,需要更多的注释工作。在这项工作中,我们重新审视了半监督目标检测(SS-OD),并确定伪标记偏见问题的SS-OD。为了解决这个问题,我们引入了无偏见的教师,这是一种简单而有效的方法,以互利的方式共同培养学生和逐渐进步的教师。再加上类平衡损失,以降低过度自信的伪标签,Unbiased Teacher在COCO标准,COCO附加和VOC数据集上不断改进最先进的方法。具体而言,当使用MS-COCO上1%的标记数据时,无偏见的教师实现了6.8个绝对mAP的改进,当使用MS-COCO上仅0.5%,1%,2%的标记数据时,实现了约10个mAP的改进。

英文摘要:

Semi-supervised learning, i.e., training networks with both labeled and unlabeled data, has made significant progress recently. However, existing works have primarily focused on image classification tasks and neglected object detection which requires more annotation effort. In this work, we revisit the Semi-Supervised Object Detection (SS-OD) and identify the pseudo-labeling bias issue in SS-OD. To address this, we introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner. Together with a class-balance loss to downweight overly confident pseudo-labels, Unbiased Teacher consistently improved state-of-the-art methods by significant margins on COCO-standard, COCO-additional, and VOC datasets. Specifically, Unbiased Teacher achieves 6.8 absolute mAP improvements against state-of-the-art method when using 1% of labeled data on MS-COCO, achieves around 10 mAP improvements against the supervised baseline when using only 0.5, 1, 2% of labeled data on MS-COCO.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑