Invariant Representation Learning for Infant Pose Estimation with Small Data
Invariant Representation Learning for Infant Pose Estimation with Small Data
复制标题
小数据婴儿姿势估计的不变表示学习
DOI：
10.1109/fg52635.2021.9666956
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
S. Ostadabbas
中科院分区：
文献类型：
--
作者：
Xiaofei Huang;Nihang Fu;Shuangjun Liu;S. Ostadabbas
婴儿运动分析是儿童早期发展研究中一个非常重要的课题。然而，尽管人体姿势估计的应用越来越广泛，但由于婴儿的身体比例和姿势的通用性存在显著差异，在大规模成人姿势数据集上训练的模型在估计婴儿姿势方面几乎没有成功。此外，隐私和安全方面的考虑阻碍了从头开始训练健壮模型所需的足够的婴儿姿势数据的可用性。为了解决这个问题，本文提出(1)构建并公开发布一个混合合成和真实婴儿姿势（SyRIP）数据集，其中包含小而多样的真实婴儿图像以及生成的合成婴儿姿势；(2)一个多阶段不变表示学习策略，该策略可以将成人姿势和合成婴儿图像的临近域的知识转移到我们的微调域适应婴儿姿势（FiDIP）估计模型中。在我们的消融研究中，在相同的网络结构下，在SyRIP数据集上训练的模型比在其他公开的婴儿姿势数据集上训练的模型有明显的改进。与不同复杂性的姿态估计骨干网络相结合，FiDIP的性能始终优于那些模型的微调版本。我们在最先进的DarkPose模型上最好的婴儿姿势估计表演者之一显示平均精度（mAP）为93.611。代码可在github.com/ostadabbas/Infant-PoseEstimation获得。SyRIP数据集可在以下网站下载：合成和真实婴儿姿势（SyRIP）..
Infant motion analysis is a topic with critical importance in early childhood development studies. However, while the applications of human pose estimation have become more and more broad, models trained on large-scale adult pose datasets are barely successful in estimating infant poses due to the significant differences in their body ratio and the versatility of their poses. Moreover, the privacy and security considerations hinder the availability of adequate infant pose data required for training of a robust model from scratch. To address this problem, this paper presents (1) building and publicly releasing a hybrid synthetic and real infant pose (SyRIP) dataset with small yet diverse real infant images as well as generated synthetic infant poses and (2) a multi-stage invariant representation learning strategy that could transfer the knowledge from the adjacent domains of adult poses and synthetic infant images into our fine-tuned domain-adapted infant pose (FiDIP) estimation model. In our ablation study, with identical network structure, models trained on SyRIP dataset show noticeable improvement over the ones trained on the only other public infant pose datasets. Integrated with pose estimation backbone networks with varying complexity, FiDIP performs consistently better than the fine-tuned versions of those models. One of our best infant pose estimation performers on the state-of-the-art DarkPose model shows mean average precision (mAP) of 93.611The code is available at: github.com/ostadabbas/Infant-PoseEstimation. The SyRIP dataset can be downloaded at: Synthetic and Real Infant Pose (SyRIP)..