Weakly Supervised Instance Segmentation On
評価指標
Average Best Overlap
mAP@0.25
mAP@0.5
mAP@0.75
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Average Best Overlap | mAP@0.25 | mAP@0.5 | mAP@0.75 | Paper Title | Repository |
|---|---|---|---|---|---|---|
| BESTIE (point label, proposal-free) | - | 66.4 | 56.1 | 30.2 | Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement | |
| BBAM | 63.0 | 76.8 | 63.7 | 31.8 | BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation | |
| WSIS_CL | 48.2 | 56.6 | 38.1 | 12.3 | Weakly Supervised Instance Segmentation by Deep Community Learning | - |
| BESTIE (image-level label, proposal-free) | - | 61.2 | 51.0 | 26.6 | Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement | |
| LIID | 50.8 | - | 48.4 | 24.9 | Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation | |
| CIM + Mask R-CNN | - | 68.7 | 55.9 | 30.9 | Complete Instances Mining for Weakly Supervised Instance Segmentation |
0 of 6 row(s) selected.