arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.04893cs.CVcs.LG
收藏

如何使用自监督学习进行精细的头部姿势估计?

How Self-Supervised Learning Can be Used for Fine-Grained Head Pose Estimation?

Tarbiat Modares University(塔比亚特·莫达雷斯大学);ICT Research Institute(信息与通信技术研究院);Iranian Research Organization for Science and Technology (IROST)(伊朗科学技术研究组织(IROST))

Mahdi Pourmirzaei, Farzaneh Esmaili, Ebrahim Mousavi, Sasan Karamizadeh, Seyedehsamaneh Shojaeilangari

摘要:

头部姿态标注的代价是提高细粒度头部姿态估计(HPE)的主要挑战。虽然自监督学习(SSL)可以解决缺乏大量标记数据的问题,但其对细粒度HPE的有效性尚未得到充分探索。本研究旨在基于两种场景评估细粒度HPE中SSL的使用情况:(1)使用SSL进行权重预训练过程,以及(2)利用HPE之外的辅助SSL损失。我们设计了一个混合多任务学习(HMTL)架构的基础上ResNet50骨干,其中这两种策略都适用。我们的实验结果表明,这两种情况的组合是最适合HPE的。总之,与基线相比,AFLW 2000的平均出错率降低了23.1%,BIWI基准降低了14.2%。此外,它被发现,一些SSL方法更适合迁移学习,而其他人可能是有效的,当他们被认为是辅助任务纳入监督学习。最后,通过使用所提出的HMTL架构,可以使用不同类型的初始权重来降低平均误差:随机,ImageNet和SSL预训练权重。

英文摘要:

The cost of head pose labeling is the main challenge of improving the fine-grained Head Pose Estimation (HPE). Although Self-Supervised Learning (SSL) can be a solution to the lack of huge amounts of labeled data, its efficacy for fine-grained HPE is not yet fully explored. This study aims to assess the usage of SSL in fine-grained HPE based on two scenarios: (1) using SSL for weights pre-training procedure, and (2) leveraging auxiliary SSL losses besides HPE. We design a Hybrid Multi-Task Learning (HMTL) architecture based on the ResNet50 backbone in which both strategies are applied. Our experimental results reveal that the combination of both scenarios is the best for HPE. Together, the average error rate is reduced up to 23.1% for AFLW2000 and 14.2% for BIWI benchmark compared to the baseline. Moreover, it is found that some SSL methods are more suitable for transfer learning, while others may be effective when they are considered as auxiliary tasks incorporated into supervised learning. Finally, it is shown that by using the proposed HMTL architecture, the average error is reduced with different types of initial weights: random, ImageNet and SSL pre-trained weights.

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。

↑