AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation

17 Aug 2020 Junjie Huang Zheng Zhu Guan Huang Dalong Du

Both appearance cue and constraint cue are vital for human pose estimation. However, there is a tendency in most existing works to overfitting the former and overlook the latter... (read more)

PDF Abstract

Datasets


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Multi-Person Pose Estimation COCO minival ResNet50 AP 75.3 # 3
Multi-Person Pose Estimation COCO minival HRNet-W32 AP 77.8 # 2
Multi-Person Pose Estimation COCO minival HRNet-W48plus AP 79.1 # 1
Multi-Person Pose Estimation COCO test-dev ResNet50 AP 73.7 # 3
Multi-Person Pose Estimation COCO test-dev HRNet-W32 AP 76.2 # 2
Multi-Person Pose Estimation COCO test-dev HRNet-W48plus AP 78.7 # 1

Methods used in the Paper


METHOD TYPE
Batch Normalization
Normalization
Residual Connection
Skip Connections
Convolution
Convolutions
ReLU
Activation Functions
HRNet
Convolutional Neural Networks