# Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation

arXiv: https://arxiv.org/abs/2203.07837 · HTML: https://mlsanity.com/paper/2203.07837/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 20 references that are in the map.
- First posted on arXiv 15 Mar 2022.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning](https://mlsanity.com/paper/2101.08482/) (2021)
- [Unsupervised learning of object landmarks by factorized spatial embeddings](https://mlsanity.com/paper/1705.02193/) (2017)
- [Structured Consistency Loss for semi-supervised semantic segmentation](https://mlsanity.com/paper/2001.04647/) (2020)
- [Multi-Scale Structure-Aware Network for Human Pose Estimation](https://mlsanity.com/paper/1803.09894/) (2018)
- [An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation](https://mlsanity.com/paper/2011.12498/) (2020)
- [MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection](https://mlsanity.com/paper/2111.10958/) (2021)

## Built on by (most cited first, 3 of 3)

- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [A Survey of Historical Learning: Learning Models with Learning History](https://mlsanity.com/paper/2303.12992/) (2023)
- [Active Semi-Supervised Learning by Exploring Per-Sample Uncertainty and Consistency](https://mlsanity.com/paper/2303.08978/) (2023)

## Abstract (arXiv)

A well-designed strong-weak augmentation strategy and the stable teacher to generate reliable pseudo labels are essential in the teacher-student framework of semi-supervised learning (SSL). Considering these in mind, to suit the semi-supervised human pose estimation (SSHPE) task, we propose a novel approach referred to as Pose-MUM that modifies Mix/UnMix (MUM) augmentation. Like MUM in the dense prediction task, the proposed Pose-MUM makes strong-weak augmentation for pose estimation and leads the network to learn the relationship between each human key point much better than the conventional methods by adding the mixing process in intermediate layers in a stochastic manner. In addition, we employ the exponential-moving-average-normalization (EMAN) teacher, which is stable and well-suited to the SSL framework and furthermore boosts the performance. Extensive experiments on MS-COCO dataset show the superiority of our proposed method by consistently improving the performance over the previous methods following SSHPE benchmark.