arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.03195cs.CV
收藏

学习从有限的标记数据中计算人群

Learning to Count in the Crowd from Limited Labeled Data

Vishwanath A. Sindagi, Rajeev Yasarla, Deepak Sam Babu, R. Venkatesh Babu, Vishal M. Patel

摘要:

最近的人群计数方法取得了优异的性能。然而,它们基本上是基于完全监督的范例,需要大量的注释样本。获取注释是一个昂贵且劳动密集型的过程。在这项工作中,我们专注于减少注释工作,通过学习从有限数量的标记样本中计数,同时利用大量的未标记数据池。具体来说,我们提出了一种基于高斯过程的迭代学习机制,该机制涉及对未标记数据的伪地面真值的估计,然后将其用作训练网络的监督。所提出的方法被证明是有效的减少数据(半监督)设置下的几个数据集,如上海科技,UCF-QNRF,世博会,UCSD等,此外,我们证明,所提出的方法可以利用,使网络在学习从合成数据集计数,同时能够更好地推广到现实世界的数据集(合成到真实的传输)。

英文摘要:

Recent crowd counting approaches have achieved excellent performance. However, they are essentially based on fully supervised paradigm and require large number of annotated samples. Obtaining annotations is an expensive and labour-intensive process. In this work, we focus on reducing the annotation efforts by learning to count in the crowd from limited number of labeled samples while leveraging a large pool of unlabeled data. Specifically, we propose a Gaussian Process-based iterative learning mechanism that involves estimation of pseudo-ground truth for the unlabeled data, which is then used as supervision for training the network. The proposed method is shown to be effective under the reduced data (semi-supervised) settings for several datasets like ShanghaiTech, UCF-QNRF, WorldExpo, UCSD, etc. Furthermore, we demonstrate that the proposed method can be leveraged to enable the network in learning to count from synthetic dataset while being able to generalize better to real-world datasets (synthetic-to-real transfer).

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。

↑