How to Train Your Robust Human Pose Estimator: Pay Attention to the Constraint Cue

08/17/2020
by   Junjie Huang, et al.
4

Both appearance cue and constraint cue are important in human pose estimation. However, the widely used response map supervision has the tendency to overfit the appearance cue and overlook the constraint cue. In this paper, we propose occlusion augmentation with customized training schedules to tackle this dilemma. Specifically, we implicitly force the neural network focus on the constraint cue by dropping appearance information within keypoint-aware strategy. Besides, a two-steps schedule is designed to deal with the information shortage in early training process, which effectively exploits the potential of the proposed occlusion augmentation. In experiments, as a model-agnostic approach, occlusion augmentation consistently promotes most SOTAs with different input sizes, frameworks, backbones, training and test sets. For HRNet within W32-256x192 and W48plus-384x288 configurations, occlusion augmentation obtains gains by 0.6 AP (75.6 to 76.2) and 0.7 AP (76.8 to 77.5) on COCO test-dev set, respectively. HRNet-W48plus-384x288 equipped with extra training data and occlusion augmentation achieves 78.7 AP. Furthermore, the proposed occlusion augmentation makes a remarkable improvement on more challenging CrowdPose dataset. The source code will be publicly available for further research in https://github.com/HuangJunJie2017/UDP-Pose.

READ FULL TEXT

page 3

page 7

research
10/20/2020

Tilting at windmills: Data augmentation for deep pose estimation does not help with occlusions

Occlusion degrades the performance of human pose estimation. In this pap...
research
04/24/2023

Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation

Occlusion is an omnipresent challenge in 3D human pose estimation (HPE)....
research
11/16/2021

Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation

In keypoint estimation tasks such as human pose estimation, heatmap-base...
research
07/26/2021

Augmentation Pathways Network for Visual Recognition

Data augmentation is practically helpful for visual recognition, especia...
research
11/18/2019

The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation

Recently, the leading performance of human pose estimation is dominated ...
research
10/23/2020

View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose

Recognition of human poses and activities is crucial for autonomous syst...
research
10/02/2020

DecAug: Augmenting HOI Detection via Decomposition

Human-object interaction (HOI) detection requires a large amount of anno...

Please sign up or login with your details

Forgot password? Click here to reset