PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation
This work addresses a domain-specific problem for human pose estimation by providing an incremental improvement to handle rare poses more effectively.
The paper tackles the problem of inferior generalization in human pose estimation due to long-tailed datasets and lack of rare pose diversity by proposing PoseTrans, a data augmentation method that creates diverse and plausible poses and balances the distribution, resulting in improved performance especially on rare poses as shown in experiments on three benchmark datasets.
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.