Image Level Supervised Instance Segmentation 1
Metrics
AP
AP@50
AP@75
Results
Performance results of various models on this benchmark
Model Name | AP | AP@50 | AP@75 | Paper Title | Repository |
|---|---|---|---|---|---|
| LIID | 16.0 | 27.1 | 16.5 | Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation | |
| WeakSAM-Mask RCNN (with SAM) | 21.0 | 34.5 | 22.2 | WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition | - |
| WeakSAM-Mask2Former (with SAM) | 25.9 | 39.9 | 27.9 | WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition | - |
| Fan et al. | 13.7 | 25.5 | 13.5 | Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation | - |
| BESTIE (proposal-free) | 14.4 | 28.0 | 13.5 | Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement | - |
| CIM | 12.0 | 23.0 | 11.3 | Complete Instances Mining for Weakly Supervised Instance Segmentation | - |
| CIM + Mask R-CNN | 17.2 | 29.7 | 17.3 | Complete Instances Mining for Weakly Supervised Instance Segmentation | - |
0 of 7 row(s) selected.