Point Supervised Instance Segmentation On
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Paper Title | Repository | ||||
|---|---|---|---|---|---|---|
| CIM + Mask R-CNN | 67.8 | 55.5 | 36.6 | 31.1 | Complete Instances Mining for Weakly Supervised Instance Segmentation | - |
| BESTIE (proposal-free) | 66.4 | 56.1 | 36.5 | 30.2 | Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement | - |
| WISE-Net | 53.5 | 43.0 | - | 25.9 | - | - |
0 of 3 row(s) selected.