Interactive Instance Segmentation on COCO (MVal)
2NoC @ 85%UCP-Net
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| UCP-NetTrain Set=SBD Train2021.09 | 2 | — | — | — | — | |
| Ours-ViT-B+MST+CLBackbone=ViT-B, MST=true, CL=true, Training Data=COCO [26] and LVIS [27]2024.01 | 2.08 | — | 2.85 | — | — | |
| Ours-ViT-B+MSTBackbone=ViT-B, MST=true, Training Data=COCO [26] and LVIS [27]2024.01 | 2.11 | — | 2.88 | — | — | |
| RITM-hrnet32Backbone=hrnet32, Training Data=COCO [26] and LVIS [27]2024.01 | 2.18 | — | 3.03 | — | — | |
| SimpleClick-ViT-BBackbone=ViT-B, Training Data=COCO [26] and LVIS [27]2024.01 | 2.18 | — | 2.92 | — | — | |
| FocalClick-segformer-B3-S2Backbone=segformer-B3-S2, Training Data=COCO [26] and LVIS [27]2024.01 | 2.45 | — | 3.33 | — | — | |
| DC-TTABackbone=ViT-B, Input Resolution=1024x1024, Max Clicks=202025.06 | 2.71 | — | 4.22 | 0.88 | 5 | |
| AdaptSAMBackbone=ViT-B, Input Resolution=1024x1024, Max Clicks=202025.06 | 2.97 | — | 4.71 | 2.88 | 9.25 | |
| BaselineBackbone=ViT-B, Input Resolution=1024x1024, Max Clicks=202025.06 | 3.01 | — | 4.84 | 3.25 | 10.38 | |
| TENTBackbone=ViT-B, Input Resolution=1024x1024, Max Clicks=202025.06 | 3.01 | — | 4.9 | 3.13 | 11 | |
| DC-onlyBackbone=ViT-B, Input Resolution=1024x1024, Max Clicks=202025.06 | 3.02 | — | 4.78 | 3.38 | 10.13 | |
| FocalClick-segformer-B0-S2Backbone=segformer-B0-S2, Training Data=COCO [26] and LVIS [27]2024.01 | 3.23 | — | 4.37 | — | — | |
| SAM-VIT-HBackbone=VIT-H, Training Data=COCO [26] and LVIS [27]2024.01 | 3.46 | — | 5.6 | — | — | |
| HQ-SAM-VIT-HBackbone=VIT-H, Training Data=COCO [26] and LVIS [27]2024.01 | 3.81 | — | 5.94 | — | — | |
| DEXTRTrain Set=SBD Full2021.09 | 4 | 80.1 | — | — | — | |
| IIS-LDTrain Set=SBD Train2021.09 | 7.86 | — | — | — | — | |
| iFCNTrain Set=VOC122021.09 | 9.07 | — | — | — | — | |
| FCTSFNTrain Set=VOC122021.09 | 9.62 | — | — | — | — | |
| RITM-hrnet18sBackbone=hrnet18s, Training Data=COCO [26] and LVIS [27]2024.01 | — | — | 3.58 | — | — |