Interactive Segmentation on SBD (test)
3.26NoC @ 85%MFP
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| MFPBackbone=ViT-B, Training Data=COCO + LVIS2024.04 | 3.26 | — | — | 5.34 | — | 11.65 | |
| iCMFormerBackbone=ViT-B, Training Data=COCO + LVIS2024.04 | 3.29 | — | — | 5.3 | — | — | |
| DynaMITeBackbone=Swin-L, Training Data=COCO + LVIS2024.04 | 3.32 | — | — | 5.64 | — | — | |
| FocalClickBackbone=SegF-B3, Training Data=COCO + LVIS2024.04 | 3.43 | — | — | 5.62 | — | 11.55 | |
| SimpleClickBackbone=ViT-B, Training Data=COCO + LVIS2024.04 | 3.43 | — | — | 5.62 | — | 11.92 | |
| PseudoClickBackbone=HRNet-32, Training Data=COCO + LVIS2024.04 | 3.46 | — | — | 5.54 | — | — | |
| EMC-ClickBackbone=HRNet-32, Training Data=COCO + LVIS2024.04 | 3.55 | — | — | 5.65 | — | 12.26 | |
| RITMBackbone=HRNet-32, Training Data=COCO + LVIS2024.04 | 3.59 | — | — | 5.71 | — | 12 | |
| CDNetBackbone=ResNet-34, Training Data=COCO + LVIS2024.04 | 4.3 | — | — | 7.04 | — | 14.17 | |
| SimpleClickBackbone=ViT-xTiny, Pretrained=false, Params/M=3.722022.10 | 4.71 | — | — | 7.09 | — | — | |
| FocalClickBackbone=HRNet-18s-S1, Pretrained=true, Params/M=4.222022.10 | 4.74 | — | — | 7.29 | — | — | |
| FocalClickBackbone=SegFormer-B0-S1, Pretrained=true, Params/M=3.722022.10 | 4.98 | — | — | 7.6 | — | — | |
| DistMap-BRSLoss Function=L_ors2021.12 | — | 0.832 | 0.894 | — | — | — | |
| DistMap-BRSLoss Function=L_c (Ours)2021.12 | — | 0.845 | 0.891 | — | — | — | |
| GraCoBackbone=ViT-B, Granularity guidance=GT, Training Dataset=SBD2024.05 | — | — | — | — | 0.66 | — | |
| GraCoBackbone=ViT-B, Granularity guidance=AGG, Training Dataset=SBD2024.05 | — | — | — | — | 0.72 | — | |
| GraCoBackbone=ViT-L, Granularity guidance=GT, Training Dataset=SBD2024.05 | — | — | — | — | 0.66 | — | |
| GraCoBackbone=ViT-L, Granularity guidance=AGG, Training Dataset=SBD2024.05 | — | — | — | — | 0.81 | — | |
| RGB-BRSLoss Function=L_ors2021.12 | — | 0.853 | 0.908 | — | — | — | |
| RGB-BRSLoss Function=L_c (Ours)2021.12 | — | 0.851 | 0.905 | — | — | — | |
| SAMBackbone=ViT-B, Best matching selection=false, Training Dataset=SA-1B2024.05 | — | — | — | — | 0.45 | — | |
| SAMBackbone=ViT-B, Best matching selection=true, Training Dataset=SA-1B2024.05 | — | — | — | — | 0.75 | — | |
| SAMBackbone=ViT-L, Best matching selection=false, Training Dataset=SA-1B2024.05 | — | — | — | — | 0.5 | — | |
| SAMBackbone=ViT-L, Best matching selection=true, Training Dataset=SA-1B2024.05 | — | — | — | — | 0.8 | — | |
| SimpleClickBackbone=ViT-B, Fine-tuning utilizing part annotation=false, Training Dataset=SBD2024.05 | — | — | — | — | 0.74 | — | |
| SimpleClickBackbone=ViT-B, Fine-tuning utilizing part annotation=true, Training Dataset=SBD2024.05 | — | — | — | — | 0.42 | — | |
| SimpleClickBackbone=ViT-L, Fine-tuning utilizing part annotation=false, Training Dataset=SBD2024.05 | — | — | — | — | 0.82 | — | |
| SimpleClickBackbone=ViT-L, Fine-tuning utilizing part annotation=true, Training Dataset=SBD2024.05 | — | — | — | — | 0.46 | — |