论文标题

PSP-HDRI $+$:用于预先培训以人为中心的计算机视觉模型的合成数据集生成器

PSP-HDRI$+$: A Synthetic Dataset Generator for Pre-Training of Human-Centric Computer Vision Models

论文作者

Ebadi, Salehe Erfanian, Dhakad, Saurav, Vishwakarma, Sanjay, Wang, Chunpu, Jhang, You-Cyuan, Chociej, Maciek, Crespi, Adam, Thaman, Alex, Ganguly, Sujoy

论文摘要

我们引入了一种新的合成数据生成器PSP-HDRI $+$,该$+$被证明是ImageNet和其他大规模合成数据对应物的优越的预训练替代方案。我们证明,使用合成数据的预训练将产生一个更通用的模型,即使在分布外(OOD)集进行测试时,该模型的性能也比替代方案更好。此外,使用由人关键点估计指标指导的消融研究,并使用现成的模型结构,我们展示了如何操纵我们的合成数据生成器以进一步提高模型性能。

We introduce a new synthetic data generator PSP-HDRI$+$ that proves to be a superior pre-training alternative to ImageNet and other large-scale synthetic data counterparts. We demonstrate that pre-training with our synthetic data will yield a more general model that performs better than alternatives even when tested on out-of-distribution (OOD) sets. Furthermore, using ablation studies guided by person keypoint estimation metrics with an off-the-shelf model architecture, we show how to manipulate our synthetic data generator to further improve model performance.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源