论文标题
后期：一种简单而有效的姿势转化增强，用于人类姿势估计
PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation
论文作者
论文摘要
人姿势估计旨在准确估计各种人类姿势。但是，现有的数据集经常遵循长尾巴的分布，而异常姿势仅占据一小部分，这进一步导致缺乏稀有姿势的多样性。这些问题导致当前姿势估计器的概括能力。在本文中，我们提出了一种简单而有效的数据增强方法，称为姿势转化（后代），以减轻上述问题。具体而言，我们建议姿势转化模块（PTM）创建具有多种姿势并采用姿势歧视者的新训练样本，以确保增强姿势的合理性。此外，我们提出姿势聚类模块（PCM）来测量姿势稀有性并选择“最稀有”姿势，以帮助平衡长尾分布。在三个基准数据集上进行的广泛实验证明了我们方法的有效性，尤其是在罕见姿势上。同样，我们的方法是有效且易于实施的，可以轻松地集成到现有姿势估计模型的训练管道中。
Human pose estimation aims to accurately estimate a wide variety of human poses. However, existing datasets often follow a long-tailed distribution that unusual poses only occupy a small portion, which further leads to the lack of diversity of rare poses. These issues result in the inferior generalization ability of current pose estimators. In this paper, we present a simple yet effective data augmentation method, termed Pose Transformation (PoseTrans), to alleviate the aforementioned problems. Specifically, we propose Pose Transformation Module (PTM) to create new training samples that have diverse poses and adopt a pose discriminator to ensure the plausibility of the augmented poses. Besides, we propose Pose Clustering Module (PCM) to measure the pose rarity and select the "rarest" poses to help balance the long-tailed distribution. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our method, especially on rare poses. Also, our method is efficient and simple to implement, which can be easily integrated into the training pipeline of existing pose estimation models.
