# Domain Adaptive Hand Keypoint and Pixel Localization in the Wild

arXiv: https://arxiv.org/abs/2203.08344 · HTML: https://mlsanity.com/paper/2203.08344/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 55 of its 83 references that are in the map.
- First posted on arXiv 16 Mar 2022.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 55)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [GRAB: A Dataset of Whole-Body Human Grasping of Objects](https://mlsanity.com/paper/2008.11200/) (2020)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [Convolutional Pose Machines](https://mlsanity.com/paper/1602.00134/) (2016)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Understanding Human Hands in Contact at Internet Scale](https://mlsanity.com/paper/2006.06669/) (2020)
- [FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images](https://mlsanity.com/paper/1909.04349/) (2019)
- [InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.09309/) (2020)
- [Learning to Estimate 3D Hand Pose from Single RGB Images](https://mlsanity.com/paper/1705.01389/) (2017)
- [Hand Keypoint Detection in Single Images using Multiview Bootstrapping](https://mlsanity.com/paper/1704.07809/) (2017)
- [First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations](https://mlsanity.com/paper/1704.02463/) (2017)
- [Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification](https://mlsanity.com/paper/2001.01526/) (2020)
- [3D Hand Shape and Pose from Images in the Wild](https://mlsanity.com/paper/1902.03451/) (2019)
- [ContactPose: A Dataset of Grasps with Object Contact and Hand Pose](https://mlsanity.com/paper/2007.09545/) (2020)
- [3D Hand Shape and Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1903.00812/) (2019)
- [Unbiased Mean Teacher for Cross-domain Object Detection](https://mlsanity.com/paper/2003.00707/) (2020)
- [Asymmetric Tri-training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.08400/) (2017)
- [GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB](https://mlsanity.com/paper/1712.01057/) (2017)
- [Deep Co-Training for Semi-Supervised Image Recognition](https://mlsanity.com/paper/1803.05984/) (2018)

## Built on by (most cited first, 14 of 14)

- [AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation](https://mlsanity.com/paper/2304.12301/) (2023)
- [Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects](https://mlsanity.com/paper/2403.16428/) (2024)
- [DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices](https://mlsanity.com/paper/2303.13325/) (2023)
- [Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation](https://mlsanity.com/paper/2403.04381/) (2024)
- [Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey](https://mlsanity.com/paper/2206.02257/) (2022)
- [Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos](https://mlsanity.com/paper/2311.16444/) (2023)
- [SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training](https://mlsanity.com/paper/2502.15251/) (2025)
- [CLIP-Hand3D: Exploiting 3D Hand Pose Estimation via Context-Aware Prompting](https://mlsanity.com/paper/2309.16140/) (2023)
- [MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection](https://mlsanity.com/paper/2302.04589/) (2023)
- [Domain-Adaptive Full-Face Gaze Estimation via Novel-View-Synthesis and Feature Disentanglement](https://mlsanity.com/paper/2305.16140/) (2023)
- [Pre-Training for 3D Hand Pose Estimation with Contrastive Learning on Large-Scale Hand Images in the Wild](https://mlsanity.com/paper/2409.09714/) (2024)
- [Fairness meets Cross-Domain Learning: a new perspective on Models and Metrics](https://mlsanity.com/paper/2303.14411/) (2023)
- [Leveraging 2D Masked Reconstruction for Domain Adaptation of 3D Pose Estimation](https://mlsanity.com/paper/2501.08408/) (2025)
- [DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions](https://mlsanity.com/paper/2512.02727/) (2025)

## Abstract (arXiv)

We aim to improve the performance of regressing hand keypoints and segmenting pixel-level hand masks under new imaging conditions (e.g., outdoors) when we only have labeled images taken under very different conditions (e.g., indoors). In the real world, it is important that the model trained for both tasks works under various imaging conditions. However, their variation covered by existing labeled hand datasets is limited. Thus, it is necessary to adapt the model trained on the labeled images (source) to unlabeled images (target) with unseen imaging conditions. While self-training domain adaptation methods (i.e., learning from the unlabeled target images in a self-supervised manner) have been developed for both tasks, their training may degrade performance when the predictions on the target images are noisy. To avoid this, it is crucial to assign a low importance (confidence) weight to the noisy predictions during self-training. In this paper, we propose to utilize the divergence of two predictions to estimate the confidence of the target image for both tasks. These predictions are given from two separate networks, and their divergence helps identify the noisy predictions. To integrate our proposed confidence estimation into self-training, we propose a teacher-student framework where the two networks (teachers) provide supervision to a network (student) for self-training, and the teachers are learned from the student by knowledge distillation. Our experiments show its superiority over state-of-the-art methods in adaptation settings with different lighting, grasping objects, backgrounds, and camera viewpoints. Our method improves by 4% the multi-task score on HO3D compared to the latest adversarial adaptation method. We also validate our method on Ego4D, egocentric videos with rapid changes in imaging conditions outdoors.