# DistilPose: Tokenized Pose Regression with Heatmap Distillation

arXiv: https://arxiv.org/abs/2303.02455 · HTML: https://mlsanity.com/paper/2303.02455/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 4 Mar 2023.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [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)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [Integral Human Pose Regression](https://mlsanity.com/paper/1711.08229/) (2017)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [Distribution-Aware Coordinate Representation for Human Pose Estimation](https://mlsanity.com/paper/1910.06278/) (2019)
- [All Tokens Matter: Token Labeling for Training Better Vision Transformers](https://mlsanity.com/paper/2104.10858/) (2021)
- [Towards Accurate Multi-person Pose Estimation in the Wild](https://mlsanity.com/paper/1701.01779/) (2017)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation](https://mlsanity.com/paper/1406.2984/) (2014)
- [TransPose: Keypoint Localization via Transformer](https://mlsanity.com/paper/2012.14214/) (2020)
- [TokenPose: Learning Keypoint Tokens for Human Pose Estimation](https://mlsanity.com/paper/2104.03516/) (2021)
- [Pose Recognition with Cascade Transformers](https://mlsanity.com/paper/2104.06976/) (2021)
- [Single-Stage Multi-Person Pose Machines](https://mlsanity.com/paper/1908.09220/) (2019)
- [The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation](https://mlsanity.com/paper/1911.07524/) (2019)
- [Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild](https://mlsanity.com/paper/2003.03771/) (2020)
- [Fast Human Pose Estimation](https://mlsanity.com/paper/1811.05419/) (2018)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [DirectPose: Direct End-to-End Multi-Person Pose Estimation](https://mlsanity.com/paper/1911.07451/) (2019)
- [Poseur: Direct Human Pose Regression with Transformers](https://mlsanity.com/paper/2201.07412/) (2022)
- [TFPose: Direct Human Pose Estimation with Transformers](https://mlsanity.com/paper/2103.15320/) (2021)
- [PE-former: Pose Estimation Transformer](https://mlsanity.com/paper/2112.04981/) (2021)

## Built on by (most cited first, 12 of 12)

- [Video-Based Human Pose Regression via Decoupled Space-Time Aggregation](https://mlsanity.com/paper/2403.19926/) (2024)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [GTPT: Group-based Token Pruning Transformer for Efficient Human Pose Estimation](https://mlsanity.com/paper/2407.10756/) (2024)
- [Diversifying Human Pose in Synthetic Data for Aerial-view Human Detection](https://mlsanity.com/paper/2405.15939/) (2024)
- [SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation](https://mlsanity.com/paper/2404.03518/) (2024)
- [Differentially Private 2D Human Pose Estimation](https://mlsanity.com/paper/2504.10190/) (2025)
- [Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.11448/) (2024)
- [Focus on Low-Resolution Information: Multi-Granular Information-Lossless Model for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.12247/) (2024)
- [AgentPose: Progressive Distribution Alignment via Feature Agent for Human Pose Distillation](https://mlsanity.com/paper/2501.08088/) (2025)
- [A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural Network](https://mlsanity.com/paper/2508.11212/) (2025)
- [SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering](https://mlsanity.com/paper/2511.08294/) (2025)
- [ER-Pose: Rethinking Keypoint-Driven Representation Learning for Real-Time Human Pose Estimation](https://mlsanity.com/paper/2603.08681/) (2026)

## Abstract (arXiv)

In the field of human pose estimation, regression-based methods have been dominated in terms of speed, while heatmap-based methods are far ahead in terms of performance. How to take advantage of both schemes remains a challenging problem. In this paper, we propose a novel human pose estimation framework termed DistilPose, which bridges the gaps between heatmap-based and regression-based methods. Specifically, DistilPose maximizes the transfer of knowledge from the teacher model (heatmap-based) to the student model (regression-based) through Token-distilling Encoder (TDE) and Simulated Heatmaps. TDE aligns the feature spaces of heatmap-based and regression-based models by introducing tokenization, while Simulated Heatmaps transfer explicit guidance (distribution and confidence) from teacher heatmaps into student models. Extensive experiments show that the proposed DistilPose can significantly improve the performance of the regression-based models while maintaining efficiency. Specifically, on the MSCOCO validation dataset, DistilPose-S obtains 71.6% mAP with 5.36M parameter, 2.38 GFLOPs and 40.2 FPS, which saves 12.95x, 7.16x computational cost and is 4.9x faster than its teacher model with only 0.9 points performance drop. Furthermore, DistilPose-L obtains 74.4% mAP on MSCOCO validation dataset, achieving a new state-of-the-art among predominant regression-based models.