Interactive Segmentation on COD10K
8.91NoC@90FocSAM-ViT-H
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| FocSAM-ViT-HBackbone=ViT-H2024.05 | 8.91 | 0.39 | — | — | — | |
| SimpleClick-ViT-LBackbone=ViT-L2024.05 | 9.07 | 3.12 | — | — | — | |
| SimpleClick-ViT-HBackbone=ViT-H2024.05 | 9.13 | 6.99 | — | — | — | |
| InterFormer-TinyModel Size=Tiny2024.05 | 9.42 | 0.23 | — | — | — | |
| SimpleClick-ViT-BBackbone=ViT-B2024.05 | 9.93 | 1.26 | — | — | — | |
| SAM-ViT-HBackbone=ViT-H, Conventional COCO+LVIS training=false2024.05 | 10.36 | 0.35 | — | — | — | |
| FocalClick-SegFB3-S2Backbone=SegFB3, Model Config=S22024.05 | 10.54 | 0.1 | — | — | — | |
| DC-TTABackbone=ViT-B, Input Resolution=1024x1024, Max Clicks=202025.06 | 10.8 | — | 7.42 | 21.62 | 39.73 | |
| DC-onlyBackbone=ViT-B, Input Resolution=1024x1024, Max Clicks=202025.06 | 11.11 | — | 7.55 | 22.9 | 42.5 | |
| InterFormer-LightModel Size=Light2024.05 | 11.27 | 0.13 | — | — | — | |
| AdaptSAMBackbone=ViT-B, Input Resolution=1024x1024, Max Clicks=202025.06 | 11.28 | — | 7.78 | 24.14 | 43.88 | |
| BaselineBackbone=ViT-B, Input Resolution=1024x1024, Max Clicks=202025.06 | 11.43 | — | 7.88 | 24.93 | 45.21 | |
| TENTBackbone=ViT-B, Input Resolution=1024x1024, Max Clicks=202025.06 | 11.44 | — | 7.89 | 25.27 | 45.06 | |
| FocalClick-HR32-S2Backbone=HR32, Model Config=S22024.05 | 11.59 | 0.14 | — | — | — | |
| FocalClick-SegFB0-S2Backbone=SegFB0, Model Config=S22024.05 | 11.77 | 0.02 | — | — | — | |
| FocalClick-HR18S-S2Backbone=HR18S, Model Config=S22024.05 | 12 | 0.07 | — | — | — | |
| FocalClick-HR18S-S1Backbone=HR18S, Model Config=S12024.05 | 13.39 | 0.03 | — | — | — | |
| FocalClick-SegFB0-S1Backbone=SegFB0, Model Config=S12024.05 | 14.01 | 0.01 | — | — | — |