arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1909.11229cs.CVcs.LG
收藏

预训练增强了姿态估计的域外鲁棒性

Pretraining boosts out-of-domain robustness for pose estimation

EPFL(洛桑联邦理工学院);Harvard University(哈佛大学);University of Tübingen(蒂宾根大学);Performance Genetics(性能遗传学公司)

Alexander Mathis, Thomas Biasi, Steffen Schneider, Mert Yüksekgönül, Byron Rogers, Matthias Bethge, Mackenzie W. Mathis

摘要:

神经网络是姿态估计的高效工具。然而,与其他计算机视觉任务一样,对域外数据的鲁棒性仍然是一个挑战,特别是对于现实世界应用中常见的小训练集。在这里,我们使用三个架构类(MobileNetV 2s,ResNets和EfficientNets)来探测姿态估计的泛化能力。我们开发了一个包含30匹马的数据集,可以进行“域内”和“域外”(看不见的马)基准测试-这是对鲁棒性的关键测试,目前的人类姿势估计基准没有直接解决。我们发现,如果先在ImageNet上进行预训练,ImageNet性能更好的架构在域内和域外数据上的表现都更好。我们还表明,更好的ImageNet模型在动物物种中具有更好的泛化能力。此外,我们还介绍了Horse-C,这是一个新的基准,用于姿势估计的常见腐败,并确认预训练也可以提高这种域转移背景下的性能。总体而言,我们的研究结果表明,迁移学习是有益的域外鲁棒性。

英文摘要:

Neural networks are highly effective tools for pose estimation. However, as in other computer vision tasks, robustness to out-of-domain data remains a challenge, especially for small training sets that are common for real-world applications. Here, we probe the generalization ability with three architecture classes (MobileNetV2s, ResNets, and EfficientNets) for pose estimation. We developed a dataset of 30 horses that allowed for both "within-domain" and "out-of-domain" (unseen horse) benchmarking - this is a crucial test for robustness that current human pose estimation benchmarks do not directly address. We show that better ImageNet-performing architectures perform better on both within- and out-of-domain data if they are first pretrained on ImageNet. We additionally show that better ImageNet models generalize better across animal species. Furthermore, we introduce Horse-C, a new benchmark for common corruptions for pose estimation, and confirm that pretraining increases performance in this domain shift context as well. Overall, our results demonstrate that transfer learning is beneficial for out-of-domain robustness.

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。

↑