Keypoint Detection On Coco

评估指标

Validation AP

评测结果

各个模型在此基准测试上的表现结果

模型名称	Validation AP	Paper Title
ResNet-50	72.2	Simple Baselines for Human Pose Estimation and Tracking
Sapiens-1B	82.1	Sapiens: Foundation for Human Vision Models
Sapiens-2B	82.2	Sapiens: Foundation for Human Vision Models
DarkPose(384x288)	-	Distribution-Aware Coordinate Representation for Human Pose Estimation
UDP-Pose-PSA(384x288)	79.5	Polarized Self-Attention: Towards High-quality Pixel-wise Regression
4xRSN-50(384×288)	-	Learning Delicate Local Representations for Multi-Person Pose Estimation
PersonLab	-	PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model
PNFS	-	Pose Neural Fabrics Search
Sapiens-0.3B	79.6	Sapiens: Foundation for Human Vision Models
MIPNet(384x288)	76.3	Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation
AlphaPose	-	RMPE: Regional Multi-person Pose Estimation
Poseur(384x288)	79.6	Poseur: Direct Human Pose Regression with Transformers
EvoPose2D-L(512x384)	77.5	EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer
Pose Residual Network	69.6	MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network
CPN+	-	Cascaded Pyramid Network for Multi-Person Pose Estimation
HRNet-48(384x288)	76.3	Deep High-Resolution Representation Learning for Human Pose Estimation
AggPose(256x192)	76.4	AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation
HRNet-32	75.8	Deep High-Resolution Representation Learning for Human Pose Estimation
MSPN(384x288)	-	Rethinking on Multi-Stage Networks for Human Pose Estimation
PoseFix(384x288)	77.3	PoseFix: Model-agnostic General Human Pose Refinement Network

0 of 24 row(s) selected.