Segmentation on Amyloid Plaque Few-shot
68Total DiceUNet
Evaluation results
| Method | Links | ||
|---|---|---|---|
| UNetPre-training Strategy=Image+text pretraining, Backbone=UNet2026.05 | 68 | 58 | |
| uSAM (b)Pre-training Strategy=Baselines, Backbone=uSAM, Method Variant=base2026.05 | 66 | 41 | |
| uSAM (l)Pre-training Strategy=Baselines, Backbone=uSAM, Method Variant=large2026.05 | 62 | 37 | |
| Swin (over)Pre-training Strategy=Image+text pretraining, Backbone=Swin, Method Variant=overfit variant2026.05 | 61 | 47 | |
| SwinPre-training Strategy=Image-only pretraining, Backbone=Swin2026.05 | 58 | 21 | |
| SwinPre-training Strategy=Trained from scratch, Backbone=Swin2026.05 | 50 | 9 | |
| UNetPre-training Strategy=Trained from scratch, Backbone=UNet2026.05 | 50 | 11 | |
| UNetPre-training Strategy=Image-only pretraining, Backbone=UNet2026.05 | 50 | 3 | |
| SwinPre-training Strategy=Image+text pretraining, Backbone=Swin2026.05 | 48 | 1 |