mlsanityData to 14 Oct 2026

Lightweight Human Pose Estimation Using Heatmap-Weighting Loss

arXiv 2205.10611 ↗First posted 21 May 2022cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent research on human pose estimation exploits complex structures to improve performance on benchmark datasets, ignoring the resource overhead and inference speed when the model is actually deployed. In this paper, we lighten the computation cost and parameters of the deconvolution head network in SimpleBaseline and introduce an attention mechanism that utilizes original, inter-level, and intra-level information to intensify the accuracy. Additionally, we propose a novel loss function called heatmap weighting loss, which generates weights for each pixel on the heatmap that makes the model more focused on keypoints. Experiments demonstrate our method achieves a balance between performance, resource volume, and inference speed. Specifically, our method can achieve 65.3 AP score on COCO test-dev, while the inference speed is 55 FPS and 18 FPS on the mobile GPU and CPU, respectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 30 references that are in the map. First posted on arXiv 21 May 2022.

Builds on

24 of 30 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2017Squeeze-and-Excitation Networkscited by 4,789
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  7. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  8. 2017Non-local Neural Networkscited by 2,293
  9. 2019Searching for MobileNetV3cited by 1,994
  10. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  11. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  12. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
12 more
  1. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  2. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  3. 2019GhostNet: More Features from Cheap Operationscited by 410
  4. 2019Selective Kernel Networkscited by 403
  5. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  6. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  7. 2014Efficient Object Localization Using Convolutional Networkscited by 227
  8. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  9. 2020Learning Delicate Local Representations for Multi-Person Pose Estimationcited by 65
  10. 2019Rethinking on Multi-Stage Networks for Human Pose Estimationcited by 58
  11. 2021ViPNAS: Efficient Video Pose Estimation via Neural Architecture Searchcited by 26
  12. 2020AnimePose: Multi-person 3D pose estimation and animationcited by 10

Built on by

Not cited yet.