Semi-Supervised Human Pose Estimation

3 papers with code • 2 benchmarks • 1 datasets

Semi-supervised human pose estimation aims to leverage the unlabelled data along with labeled data to improve the model performance.


Most implemented papers

An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation

xierc/Semi_Human_Pose ICCV 2021

The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for images under different augmentations.

Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room

camma-public/hpe-adaptor 26 Aug 2021

Second, to address the domain shift and the lack of annotations, we propose a novel unsupervised domain adaptation method, called AdaptOR, to adapt a model from an in-the-wild labeled source domain to a statistically different unlabeled target domain.

Semi-supervised Human Pose Estimation in Art-historical Images

tibhannover/iart-semi-pose 6 Jul 2022

In contrast to previous work that attempts to bridge the domain gap with pre-trained models or through style transfer, we suggest semi-supervised learning for both object and keypoint detection.