Interactive Segmentation On Grabcut
Metrics
NoC@85
NoC@90
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | NoC@85 | NoC@90 |
|---|---|---|
| simpleclick-interactive-image-segmentation | 1.32 | 1.40 |
| regional-interactive-image-segmentation | - | 5.00 |
| cfr-icl-cascade-forward-refinement-with | - | 1.42 |
| deep-interactive-object-selection | 8.02 | 12.59 |
| interactive-image-segmentation-via | 2.60 | 3.60 |
| content-aware-multi-level-guidance-for | - | 3.58 |
| interactive-image-segmentation-with-latent | 3.20 | 4.79 |
| mst-adaptive-multi-scale-tokens-guided | - | 1.48 |
| reviving-iterative-training-with-mask | 1.42 | 1.54 |
| edgeflow-achieving-practical-interactive | 1.6 | 1.72 |
| ucp-net-unstructured-contour-points-for | 2 | 2.76 |
| reviving-iterative-training-with-mask | 1.76 | 2.04 |
| cfr-icl-cascade-forward-refinement-with | 1.30 | 1.32 |
| continuous-adaptation-for-interactive-object | - | 3.07 |
| f-brs-rethinking-backpropagating-refinement | 2 | 2.46 |
| intention-aware-feature-propagation-network | - | 1.68 |
| simpleclick-interactive-image-segmentation | 1.32 | 1.44 |
| deep-interactive-object-selection | 5.08 | 6.08 |