Segmentation on Cell Nucleus Few-shot
80Total DiceUNet
Evaluation results
| Method | Links | ||
|---|---|---|---|
| UNetPre-training Strategy=Image-only pretraining, Backbone=UNet2026.05 | 80 | 87 | |
| SwinPre-training Strategy=Image+text pretraining, Backbone=Swin2026.05 | 80 | 93 | |
| Cellpose (3D)Pre-training Strategy=Baselines, Backbone=Cellpose2026.05 | 79 | 80 | |
| Swin (over)Pre-training Strategy=Image+text pretraining, Backbone=Swin, Method Variant=overfit variant2026.05 | 79 | 96 | |
| SwinPre-training Strategy=Trained from scratch, Backbone=Swin2026.05 | 78 | 95 | |
| UNetPre-training Strategy=Image+text pretraining, Backbone=UNet2026.05 | 78 | 91 | |
| SwinPre-training Strategy=Image-only pretraining, Backbone=Swin2026.05 | 76 | 94 | |
| UNetPre-training Strategy=Trained from scratch, Backbone=UNet2026.05 | 75 | 86 | |
| Cellpose (2D)Pre-training Strategy=Baselines, Backbone=Cellpose2026.05 | 54 | 20 | |
| uSAM (l)Pre-training Strategy=Baselines, Backbone=uSAM, Method Variant=large2026.05 | 53 | 12 | |
| CellSeg3DPre-training Strategy=Baselines, Backbone=CellSeg3D2026.05 | 51 | 71 | |
| uSAM (b)Pre-training Strategy=Baselines, Backbone=uSAM, Method Variant=base2026.05 | 49 | 0 |