Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bose, Sarosij, Cruz, Hannah Dela, Dutta, Arindam, Kokkoni, Elena, Karydis, Konstantinos, Roy-Chowdhury, Amit K.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915233397735424
author Bose, Sarosij
Cruz, Hannah Dela
Dutta, Arindam
Kokkoni, Elena
Karydis, Konstantinos
Roy-Chowdhury, Amit K.
author_facet Bose, Sarosij
Cruz, Hannah Dela
Dutta, Arindam
Kokkoni, Elena
Karydis, Konstantinos
Roy-Chowdhury, Amit K.
contents 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: https://sarosijbose.github.io/SHIFT.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05789
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation
Bose, Sarosij
Cruz, Hannah Dela
Dutta, Arindam
Kokkoni, Elena
Karydis, Konstantinos
Roy-Chowdhury, Amit K.
Computer Vision and Pattern Recognition
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: https://sarosijbose.github.io/SHIFT.
title Leveraging Synthetic Adult Datasets for Unsupervised Infant Pose Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.05789