Human pose estimation is a critical tool across a variety of healthcare applications. Despite significant progress in pose estimation algorithms targeting adults, such developments for infants remain limited. Existing algorithms for infant pose estimation, despite achieving commendable performance, depend on fully supervised approaches that require large amounts of labeled data. These algorithms also struggle with poor generalizability under distribution shifts. To address these challenges, we introduce SHIFT: Leveraging SyntHetic Adult Datasets for Unsupervised InFanT Pose Estimation, which leverages the pseudo-labeling-based Mean-Teacher framework to compensate for the lack of labeled data and addresses distribution shifts by enforcing consistency between the student and the teacher pseudo-labels. Additionally, to penalize implausible predictions obtained from the mean-teacher framework, we incorporate an infant manifold pose prior. To enhance SHIFT's self-occlusion perception ability, we propose a novel visibility consistency module for improved alignment of the predicted poses with the original image. Extensive experiments on multiple benchmarks show that SHIFT significantly outperforms existing state-of-the-art unsupervised domain adaptation (UDA) pose estimation methods by 5% and supervised infant pose estimation methods by a margin of 16%. The project page is available at:this https URL.
View on arXiv@article{bose2025_2504.05789,
title={ Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation },
author={ Sarosij Bose and Hannah Dela Cruz and Arindam Dutta and Elena Kokkoni and Konstantinos Karydis and Amit K. Roy-Chowdhury },
journal={arXiv preprint arXiv:2504.05789},
year={ 2025 }
}