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 2305.09401cs.CVcs.AI
收藏

扩散数据集生成:迈向缩小行人检测的Sim2Real差距

Diffusion Dataset Generation: Towards Closing the Sim2Real Gap for Pedestrian Detection

Andrew Farley, Mohsen Zand, Michael Greenspan

AI总结:

提出一种基于扩散模型生成数据并与模拟数据混合增强的方法,有效缩小了行人检测的sim2real差距,使真实世界数据中的检测平均精度提升达27.3%。

摘要:

我们提出了一种使用扩散模型增强模拟数据集的方法,以提升真实世界数据中行人检测的性能。在真实世界中收集和标注数据的高成本促使人们使用仿真平台来创建训练数据集。虽然模拟数据收集和标注成本低廉,但遗憾的是它并不总是与真实世界数据的分布紧密匹配,这被称为sim2real差距。在本文中,我们提出了一种新颖的合成数据创建方法,旨在缩小具有挑战性的行人检测任务的sim2real差距。我们的方法使用基于扩散的架构来学习真实世界分布,一旦训练完成,该架构即被用于生成数据集。我们将这种生成的数据与模拟数据混合作为一种增强形式,并表明,与仅在纯模拟数据上训练相比,在生成数据和模拟数据的组合上进行训练,可使真实世界数据中的行人检测模型的平均精度提升高达27.3%。

英文摘要:

We propose a method that augments a simulated dataset using diffusion models to improve the performance of pedestrian detection in real-world data. The high cost of collecting and annotating data in the real-world has motivated the use of simulation platforms to create training datasets. While simulated data is inexpensive to collect and annotate, it unfortunately does not always closely match the distribution of real-world data, which is known as the sim2real gap. In this paper we propose a novel method of synthetic data creation meant to close the sim2real gap for the challenging pedestrian detection task. Our method uses a diffusion-based architecture to learn a real-world distribution which, once trained, is used to generate datasets. We mix this generated data with simulated data as a form of augmentation and show that training on a combination of generated and simulated data increases average precision by as much as 27.3% for pedestrian detection models in real-world data, compared against training on purely simulated 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。

↑