# AgentPose: Progressive Distribution Alignment via Feature Agent for Human Pose Distillation

arXiv: https://arxiv.org/abs/2501.08088 · HTML: https://mlsanity.com/paper/2501.08088/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 14 Jan 2025.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://mlsanity.com/paper/2303.07399/) (2023)
- [Densely Guided Knowledge Distillation using Multiple Teacher Assistants](https://mlsanity.com/paper/2009.08825/) (2020)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [Parameter-Efficient and Student-Friendly Knowledge Distillation](https://mlsanity.com/paper/2205.15308/) (2022)
- [Switchable Online Knowledge Distillation](https://mlsanity.com/paper/2209.04996/) (2022)
- [ResKD: Residual-Guided Knowledge Distillation](https://mlsanity.com/paper/2006.04719/) (2020)
- [2D Human Pose Estimation: A Survey](https://mlsanity.com/paper/2204.07370/) (2022)
- [DistilPose: Tokenized Pose Regression with Heatmap Distillation](https://mlsanity.com/paper/2303.02455/) (2023)

## Abstract (arXiv)

Pose distillation is widely adopted to reduce model size in human pose estimation. However, existing methods primarily emphasize the transfer of teacher knowledge while often neglecting the performance degradation resulted from the curse of capacity gap between teacher and student. To address this issue, we propose AgentPose, a novel pose distillation method that integrates a feature agent to model the distribution of teacher features and progressively aligns the distribution of student features with that of the teacher feature, effectively overcoming the capacity gap and enhancing the ability of knowledge transfer. Our comprehensive experiments conducted on the COCO dataset substantiate the effectiveness of our method in knowledge transfer, particularly in scenarios with a high capacity gap.