Toward fast and accurate human pose estimation via soft-gated skip connections

02/25/2020
by   Adrian Bulat, et al.
0

This paper is on highly accurate and highly efficient human pose estimation. Recent works based on Fully Convolutional Networks (FCNs) have demonstrated excellent results for this difficult problem. While residual connections within FCNs have proved to be quintessential for achieving high accuracy, we re-analyze this design choice in the context of improving both the accuracy and the efficiency over the state-of-the-art. In particular, we make the following contributions: (a) We propose gated skip connections with per-channel learnable parameters to control the data flow for each channel within the module within the macro-module. (b) We introduce a hybrid network that combines the HourGlass and U-Net architectures which minimizes the number of identity connections within the network and increases the performance for the same parameter budget. Our model achieves state-of-the-art results on the MPII and LSP datasets. In addition, with a reduction of 3x in model size and complexity, we show no decrease in performance when compared to the original HourGlass network.

READ FULL TEXT

page 1

page 3

page 4

research
01/22/2020

UniPose: Unified Human Pose Estimation in Single Images and Videos

We propose UniPose, a unified framework for human pose estimation, based...
research
07/29/2023

Iterative Graph Filtering Network for 3D Human Pose Estimation

Graph convolutional networks (GCNs) have proven to be an effective appro...
research
11/01/2021

Higher-Order Implicit Fairing Networks for 3D Human Pose Estimation

Estimating a 3D human pose has proven to be a challenging task, primaril...
research
03/20/2022

3D Human Pose Estimation Using Möbius Graph Convolutional Networks

3D human pose estimation is fundamental to understanding human behavior....
research
07/16/2020

EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation

Recent years have brought great advancement in 2D human pose estimation....
research
06/26/2019

Accelerating Large-Kernel Convolution Using Summed-Area Tables

Expanding the receptive field to capture large-scale context is key to o...
research
02/09/2023

To Perceive or Not to Perceive: Lightweight Stacked Hourglass Network

Human pose estimation (HPE) is a classical task in computer vision that ...

Please sign up or login with your details

Forgot password? Click here to reset