Human Part Segmentation On Pascal Person Part
Metrics
mIoU
Results
Performance results of various models on this benchmark
Model Name | mIoU | Paper Title | Repository |
|---|---|---|---|
| Joint (ResNet-101, +ms) | 64.39 | Joint Multi-Person Pose Estimation and Semantic Part Segmentation | - |
| SCHP | 71.46 | Self-Correction for Human Parsing | |
| WSHP | 67.60 | Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer | |
| HAZN | 57.54 | Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net | - |
| Joint (VGG-16, +ms) | 58.06 | Joint Multi-Person Pose Estimation and Semantic Part Segmentation | - |
| CDCL | 65.02 | Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation | |
| CDCL+Pascal | 72.82 | Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation |
0 of 7 row(s) selected.