PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation

TL;DR

PoseTrans is a simple data augmentation technique that generates diverse and plausible human poses to improve the generalization of pose estimation models, especially for rare poses, by balancing dataset distribution.

Contribution

The paper introduces PoseTrans, combining pose transformation and clustering modules, to augment data and address long-tailed pose distributions in human pose estimation.

Findings

Improves accuracy on rare poses in benchmark datasets.

Easily integrates into existing pose estimation training pipelines.

Effective in balancing pose distribution and enhancing model generalization.

Abstract

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.