论文标题
LOOC：通过计数监督本地化重叠对象
LOOC: Localize Overlapping Objects with Count Supervision
论文作者
论文摘要
获取计数注释通常需要比点级和边界框注释要少的人为努力。因此，我们提出了在这个较弱的监督下，在密集的场景中定位对象的新型问题。我们提出了LOOC，这是一种通过计数监督定位重叠对象的方法。我们通过在两个阶段之间交替训练LOOC。在第一阶段，LOOC学会了以半监督的方式生成伪点级注释。在第二阶段，LOOC使用了完全监督的定位方法，该方法在这些伪标签上训练。定位方法用于逐步提高伪标签的质量。我们对流行的计数数据集进行了实验。对于本地化，LOOC在新的问题设置中实现了强大的新基线，在此设置中，只有计数监督。为了计数，LOOC优于仅使用算作其监督的当前最新方法。代码可在以下网址获得：https：//github.com/elementai/looc。
Acquiring count annotations generally requires less human effort than point-level and bounding box annotations. Thus, we propose the novel problem setup of localizing objects in dense scenes under this weaker supervision. We propose LOOC, a method to Localize Overlapping Objects with Count supervision. We train LOOC by alternating between two stages. In the first stage, LOOC learns to generate pseudo point-level annotations in a semi-supervised manner. In the second stage, LOOC uses a fully-supervised localization method that trains on these pseudo labels. The localization method is used to progressively improve the quality of the pseudo labels. We conducted experiments on popular counting datasets. For localization, LOOC achieves a strong new baseline in the novel problem setup where only count supervision is available. For counting, LOOC outperforms current state-of-the-art methods that only use count as their supervision. Code is available at: https://github.com/ElementAI/looc.
