Interactive Image Segmentation on SBD
4.44NoC90SAM-REF
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SAM-REFTrain data=COCO+LVIS, Backbone=ViT-H*, SPC/s=0.511, Fusion Strategy=Late Fusion2024.08 | 4.44 | 10.41 | |
| AdaptiveClickTrain data=COCO+LVIS, Backbone=VIT-H, Fusion Strategy=Early Fusion2024.08 | 4.68 | — | |
| SimpleClickTrain data=COCO+LVIS, Backbone=VIT-H, SPC/s=8.24, Fusion Strategy=Early Fusion2024.08 | 4.7 | 10.76 | |
| FocSAMTrain data=COCO+LVIS, Backbone=VIT-H*, SPC/s=0.467, Fusion Strategy=Late Fusion2024.08 | 5.07 | 11.67 | |
| InterFormerTrain data=COCO+LVIS, Backbone=VIT-L, SPC/s=0.271, Fusion Strategy=Late Fusion2024.08 | 5.51 | — | |
| PseudoClickTrain data=COCO+LVIS, Backbone=HRNet32, Fusion Strategy=Early Fusion2024.08 | 5.54 | — | |
| CDNetTrain data=COCO+LVIS, Backbone=ResNet, Fusion Strategy=Early Fusion2024.08 | 5.56 | — | |
| SAM-REFTrain data=COCO+LVIS, Backbone=ViT-B*, SPC/s=0.278, Fusion Strategy=Late Fusion2024.08 | 5.56 | 11.76 | |
| FocalClickTrain data=COCO+LVIS, Backbone=SegFB3-S2384, SPC/s=0.232, Fusion Strategy=Early Fusion2024.08 | 5.59 | 11.91 | |
| RITMTrain data=COCO+LVIS, Backbone=HRNet32, Fusion Strategy=Early Fusion2024.08 | 5.71 | 12 | |
| EdgeFlowTrain data=COCO+LVIS, Backbone=HRNet18, Fusion Strategy=Early Fusion2024.08 | 5.77 | — | |
| InterFormerTrain data=COCO+LVIS, Backbone=VIT-B, SPC/s=0.153, Fusion Strategy=Late Fusion2024.08 | 6.34 | — | |
| SAM-REFTrain data=HQSeg-44K, Backbone=ViT-H*, SPC/s=0.511, Fusion Strategy=Late Fusion2024.08 | 6.81 | 12.18 | |
| SAMTrain data=SA-1B, Backbone=ViT-H, SPC/s=0.413, Fusion Strategy=Late Fusion2024.08 | 7.62 | 15.03 | |
| F-BRSTrain data=COCO+LVIS, Backbone=ResNet, Fusion Strategy=Early Fusion2024.08 | 7.73 | — | |
| HQ-SAMTrain data=HQSeg-44K, Backbone=ViT-H*, SPC/s=0.443, Fusion Strategy=Late Fusion2024.08 | 7.91 | 15.08 |