# Pushing the Envelope for Depth-Based Semi-Supervised 3D Hand Pose Estimation with Consistency Training

arXiv: https://arxiv.org/abs/2303.15147 · HTML: https://mlsanity.com/paper/2303.15147/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 67 references that are in the map.
- First posted on arXiv 27 Mar 2023.

## Builds on (most cited first, 30 of 41)

- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017)
- [CoMatch: Semi-supervised Learning with Contrastive Graph Regularization](https://mlsanity.com/paper/2011.11183/) (2020)
- [Deep Self-Learning From Noisy Labels](https://mlsanity.com/paper/1908.02160/) (2019)
- [Learning by Transduction](https://mlsanity.com/paper/1301.7375/) (2013)
- [Hand Pose Estimation via Latent 2.5D Heatmap Regression](https://mlsanity.com/paper/1804.09534/) (2018)
- [V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map](https://mlsanity.com/paper/1711.07399/) (2017)
- [Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning](https://mlsanity.com/paper/2101.08482/) (2021)
- [A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image](https://mlsanity.com/paper/1908.09999/) (2019)
- [All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training](https://mlsanity.com/paper/2104.05248/) (2021)
- [HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Map](https://mlsanity.com/paper/2004.01588/) (2020)
- [Generalized Feedback Loop for Joint Hand-Object Pose Estimation](https://mlsanity.com/paper/1903.10883/) (2019)
- [AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergence](https://mlsanity.com/paper/2011.11779/) (2020)
- [Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals](https://mlsanity.com/paper/1712.03917/) (2017)
- [Point-to-Pose Voting based Hand Pose Estimation using Residual Permutation Equivariant Layer](https://mlsanity.com/paper/1812.02050/) (2018)
- [Hands Deep in Deep Learning for Hand Pose Estimation](https://mlsanity.com/paper/1502.06807/) (2015)
- [JGR-P2O: Joint Graph Reasoning based Pixel-to-Offset Prediction Network for 3D Hand Pose Estimation from a Single Depth Image](https://mlsanity.com/paper/2007.04646/) (2020)
- [DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation](https://mlsanity.com/paper/1708.08325/) (2017)
- [Dense 3D Regression for Hand Pose Estimation](https://mlsanity.com/paper/1711.08996/) (2017)

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

- [HandS3C: 3D Hand Mesh Reconstruction with State Space Spatial Channel Attention from RGB images](https://mlsanity.com/paper/2405.01066/) (2024)

## Abstract (arXiv)

Despite the significant progress that depth-based 3D hand pose estimation methods have made in recent years, they still require a large amount of labeled training data to achieve high accuracy. However, collecting such data is both costly and time-consuming. To tackle this issue, we propose a semi-supervised method to significantly reduce the dependence on labeled training data. The proposed method consists of two identical networks trained jointly: a teacher network and a student network. The teacher network is trained using both the available labeled and unlabeled samples. It leverages the unlabeled samples via a loss formulation that encourages estimation equivariance under a set of affine transformations. The student network is trained using the unlabeled samples with their pseudo-labels provided by the teacher network. For inference at test time, only the student network is used. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art semi-supervised methods by large margins.