# EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search

arXiv: https://arxiv.org/abs/2012.07086 · HTML: https://mlsanity.com/paper/2012.07086/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2020.

## Built on by (most cited first, 10 of 10)

- [PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation](https://mlsanity.com/paper/2209.08194/) (2022)
- [ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2208.11547/) (2022)
- [ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimation](https://mlsanity.com/paper/2111.10524/) (2021)
- [Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation](https://mlsanity.com/paper/2205.01271/) (2022)
- [Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search](https://mlsanity.com/paper/2304.05405/) (2023)
- [Automated Deepfake Detection](https://mlsanity.com/paper/2106.10705/) (2021)
- [MamKPD: A Simple Mamba Baseline for Real-Time 2D Keypoint Detection](https://mlsanity.com/paper/2412.01422/) (2024)
- [Efficient Human Pose Estimation by Maximizing Fusion and High-Level Spatial Attention](https://mlsanity.com/paper/2107.13693/) (2021)
- [Rethinking Deconvolution for 2D Human Pose Estimation Light yet Accurate Model for Real-time Edge Computing](https://mlsanity.com/paper/2111.04226/) (2021)
- [Markerless Stride Length estimation in Athletic using Pose Estimation with monocular vision](https://mlsanity.com/paper/2507.03016/) (2025)

## Abstract (arXiv)

Human pose estimation from image and video is a vital task in many multimedia applications. Previous methods achieve great performance but rarely take efficiency into consideration, which makes it difficult to implement the networks on resource-constrained devices. Nowadays real-time multimedia applications call for more efficient models for better interactions. Moreover, most deep neural networks for pose estimation directly reuse the networks designed for image classification as the backbone, which are not yet optimized for the pose estimation task. In this paper, we propose an efficient framework targeted at human pose estimation including two parts, the efficient backbone and the efficient head. By implementing the differentiable neural architecture search method, we customize the backbone network design for pose estimation and reduce the computation cost with negligible accuracy degradation. For the efficient head, we slim the transposed convolutions and propose a spatial information correction module to promote the performance of the final prediction. In experiments, we evaluate our networks on the MPII and COCO datasets. Our smallest model has only 0.65 GFLOPs with 88.1% PCKh@0.5 on MPII and our large model has only 2 GFLOPs while its accuracy is competitive with the state-of-the-art large model, i.e., HRNet with 9.5 GFLOPs.