FasterPose: A Faster Simple Baseline for Human Pose Estimation

by   Hanbin Dai, et al.

The performance of human pose estimation depends on the spatial accuracy of keypoint localization. Most existing methods pursue the spatial accuracy through learning the high-resolution (HR) representation from input images. By the experimental analysis, we find that the HR representation leads to a sharp increase of computational cost, while the accuracy improvement remains marginal compared with the low-resolution (LR) representation. In this paper, we propose a design paradigm for cost-effective network with LR representation for efficient pose estimation, named FasterPose. Whereas the LR design largely shrinks the model complexity, yet how to effectively train the network with respect to the spatial accuracy is a concomitant challenge. We study the training behavior of FasterPose, and formulate a novel regressive cross-entropy (RCE) loss function for accelerating the convergence and promoting the accuracy. The RCE loss generalizes the ordinary cross-entropy loss from the binary supervision to a continuous range, thus the training of pose estimation network is able to benefit from the sigmoid function. By doing so, the output heatmap can be inferred from the LR features without loss of spatial accuracy, while the computational cost and model size has been significantly reduced. Compared with the previously dominant network of pose estimation, our method reduces 58 Extensive experiments show that FasterPose yields promising results on the common benchmarks, i.e., COCO and MPII, consistently validating the effectiveness and efficiency for practical utilization, especially the low-latency and low-energy-budget applications in the non-GPU scenarios.


page 2

page 4


Deep High-Resolution Representation Learning for Human Pose Estimation

This is an official pytorch implementation of Deep High-Resolution Repre...

Anchor Loss: Modulating Loss Scale based on Prediction Difficulty

We propose a novel loss function that dynamically rescales the cross ent...

Dual Path Networks for Multi-Person Human Pose Estimation

The task of multi-person human pose estimation in natural scenes is quit...

Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimation

Bottom-up based multi-person pose estimation approaches use heatmaps wit...

A Mathematical Analysis of Learning Loss for Active Learning in Regression

Active learning continues to remain significant in the industry since it...

3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning

3D human shape and pose estimation from monocular images has been an act...

JUMPS: Joints Upsampling Method for Pose Sequences

Human Pose Estimation is a low-level task useful for surveillance, human...

Please sign up or login with your details

Forgot password? Click here to reset