剪切,粘贴和学习:令人惊讶的简单合成实例检测
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection
摘要:
快速部署用于实例检测的目标检测模型的一个主要障碍是缺乏大型注释数据集。例如,在特定厨房中找到包含实例的大型标记数据集是不太可能的。每个具有新实例的新环境都需要昂贵的数据汇集和注释。在本文中,我们提出了一种简单的方法来生成大型注释的实例数据集,以最小的努力。我们的关键见解是,确保只有补丁级的现实主义提供了足够的训练信号,为当前的对象检测器模型。我们自动“剪切”对象实例并将其“粘贴”到随机背景上。一种简单的方法会导致像素伪影,从而导致训练模型的性能较差。我们展示了如何让检测器在训练过程中忽略这些伪影,并生成在真实数据上具有竞争力的数据。我们的方法优于现有的合成方法,当与真实图像相结合时,在基准数据集上的相对性能提高了21%以上。在跨域设置中,我们的合成数据与仅10%的真实数据相结合,优于所有真实数据训练的模型。
英文摘要:
A major impediment in rapidly deploying object detection models for instance detection is the lack of large annotated datasets. For example, finding a large labeled dataset containing instances in a particular kitchen is unlikely. Each new environment with new instances requires expensive data collection and annotation. In this paper, we propose a simple approach to generate large annotated instance datasets with minimal effort. Our key insight is that ensuring only patch-level realism provides enough training signal for current object detector models. We automatically `cut' object instances and `paste' them on random backgrounds. A naive way to do this results in pixel artifacts which result in poor performance for trained models. We show how to make detectors ignore these artifacts during training and generate data that gives competitive performance on real data. Our method outperforms existing synthesis approaches and when combined with real images improves relative performance by more than 21% on benchmark datasets. In a cross-domain setting, our synthetic data combined with just 10% real data outperforms models trained on all real data.
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。