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
比較表
| モデル名 | Average Best Overlap | mAP@0.25 | mAP@0.5 | mAP@0.75 |
|---|---|---|---|---|
| beyond-semantic-to-instance-segmentation | - | 66.4 | 56.1 | 30.2 |
| bbam-bounding-box-attribution-map-for-weakly | 63.0 | 76.8 | 63.7 | 31.8 |
| weakly-supervised-instance-segmentation-by | 48.2 | 56.6 | 38.1 | 12.3 |
| beyond-semantic-to-instance-segmentation | - | 61.2 | 51.0 | 26.6 |
| leveraging-instance-image-and-dataset-level | 50.8 | - | 48.4 | 24.9 |
| complete-instances-mining-for-weakly-1 | - | 68.7 | 55.9 | 30.9 |