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

10/20/2021
by   Haiyang Liu, et al.
10

Bottom-up based multi-person pose estimation approaches use heatmaps with auxiliary predictions to estimate joint positions and belonging at one time. Recently, various combinations between auxiliary predictions and heatmaps have been proposed for higher performance, these predictions are supervised by the corresponding L2 loss function directly. However, the lack of more explicit supervision results in low features utilization and contradictions between predictions in one model. To solve these problems, this paper proposes (i) a new loss organization method which uses self-supervised heatmaps to reduce prediction contradictions and spatial-sequential attention to enhance networks' features extraction; (ii) a new combination of predictions composed by heatmaps, Part Affinity Fields (PAFs) and our block-inside offsets to fix pixel-level joints positions and further demonstrates the effectiveness of proposed loss function. Experiments are conducted on the MS COCO keypoint dataset and adopting OpenPose as the baseline model. Our method outperforms the baseline overall. On the COCO verification dataset, the mAP of OpenPose trained with our proposals outperforms the OpenPose baseline by over 5.5

READ FULL TEXT

page 1

page 3

page 4

page 5

page 7

page 10

page 11

page 12

research
11/24/2019

Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation

We rethink a well-know bottom-up approach for multi-person pose estimati...
research
09/11/2019

DNANet: De-Normalized Attention Based Multi-Resolution Network for Human Pose Estimation

Recently, multi-resolution networks (such as Hourglass, CPN, HRNet, etc....
research
07/07/2021

FasterPose: A Faster Simple Baseline for Human Pose Estimation

The performance of human pose estimation depends on the spatial accuracy...
research
12/13/2020

Learning Heatmap-Style Jigsaw Puzzles Provides Good Pretraining for 2D Human Pose Estimation

The target of 2D human pose estimation is to locate the keypoints of bod...
research
05/14/2019

A Context-and-Spatial Aware Network for Multi-Person Pose Estimation

Multi-person pose estimation is a fundamental yet challenging task in co...
research
03/29/2022

On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation

Supervised approaches to 3D pose estimation from single images are remar...
research
11/08/2018

Improving Multi-Person Pose Estimation using Label Correction

Significant attention is being paid to multi-person pose estimation meth...

Please sign up or login with your details

Forgot password? Click here to reset