# Domain adaptive pose estimation via multi-level alignment

arXiv: https://arxiv.org/abs/2404.14885 · HTML: https://mlsanity.com/paper/2404.14885/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 30 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation](https://mlsanity.com/paper/2212.01322/) (2022)
- [Cross-Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/1908.05806/) (2019)
- [Learning from Synthetic Animals](https://mlsanity.com/paper/1912.08265/) (2019)
- [From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/2103.14843/) (2021)
- [Regressive Domain Adaptation for Unsupervised Keypoint Detection](https://mlsanity.com/paper/2103.06175/) (2021)
- [TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors](https://mlsanity.com/paper/2105.04605/) (2021)
- [A Unified Framework for Domain Adaptive Pose Estimation](https://mlsanity.com/paper/2204.00172/) (2022)
- [Source-free Domain Adaptive Human Pose Estimation](https://mlsanity.com/paper/2308.03202/) (2023)
- [Articulated motion discovery using pairs of trajectories](https://mlsanity.com/paper/1411.7883/) (2014)

## Built on by (most cited first, 1 of 1)

- [From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras](https://mlsanity.com/paper/2507.22438/) (2025)

## Abstract (arXiv)

Domain adaptive pose estimation aims to enable deep models trained on source domain (synthesized) datasets produce similar results on the target domain (real-world) datasets. The existing methods have made significant progress by conducting image-level or feature-level alignment. However, only aligning at a single level is not sufficient to fully bridge the domain gap and achieve excellent domain adaptive results. In this paper, we propose a multi-level domain adaptation aproach, which aligns different domains at the image, feature, and pose levels. Specifically, we first utilize image style transer to ensure that images from the source and target domains have a similar distribution. Subsequently, at the feature level, we employ adversarial training to make the features from the source and target domains preserve domain-invariant characeristics as much as possible. Finally, at the pose level, a self-supervised approach is utilized to enable the model to learn diverse knowledge, implicitly addressing the domain gap. Experimental results demonstrate that significant imrovement can be achieved by the proposed multi-level alignment method in pose estimation, which outperforms previous state-of-the-art in human pose by up to 2.4% and animal pose estimation by up to 3.1% for dogs and 1.4% for sheep.