Lightweight Human Pose Estimation Using Heatmap-Weighting Loss

05/21/2022
by   Shiqi Li, et al.
0

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.

READ FULL TEXT
research
11/23/2019

Simple and Lightweight Human Pose Estimation

Recent research on human pose estimation has achieved significant improv...
research
04/06/2021

SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation

The practical application requests both accuracy and efficiency on multi...
research
12/05/2022

2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints

Recently, human pose estimation mainly focuses on how to design a more e...
research
11/08/2021

Rethinking Deconvolution for 2D Human Pose Estimation Light yet Accurate Model for Real-time Edge Computing

In this study, we present a pragmatic lightweight pose estimation model....
research
07/29/2021

Efficient Human Pose Estimation by Maximizing Fusion and High-Level Spatial Attention

In this paper, we propose an efficient human pose estimation network – S...
research
08/17/2023

MovePose: A High-performance Human Pose Estimation Algorithm on Mobile and Edge Devices

We present MovePose, an optimized lightweight convolutional neural netwo...
research
04/01/2021

Confidence Adaptive Anytime Pixel-Level Recognition

Anytime inference requires a model to make a progression of predictions ...

Please sign up or login with your details

Forgot password? Click here to reset