Multi-class medical image segmentation on Pelvic1K CLINIC (test) benchmark leaderboard · SOTA2 Research

Multi-class medical image segmentation on Pelvic1K CLINIC (test)

99.03Dice (Left)GUMP-Net

Evaluation Results

Method	Links
GUMP-Net2026.06		99.03	99.01	97.64	98.17	98.2	96.05	1.96	2.07	1.75	0.13	0.12	0.18
U-Net2026.06		98.67	98.11	93.2	97.77	97.17	91.52	2.76	3.31	2.95	0.2	0.25	0.41
PottsMGNet2026.06		98.06	95.71	93.07	97.15	94.84	91.18	2.4	2.05	4.1	0.12	0.18	0.57
Attention U-Net2026.06		97.04	98.41	95.64	95.94	97.32	93.89	3.58	2.08	2.9	0.43	0.15	0.32
nnU-Net2026.06		97.01	96.18	92.2	95.89	95.1	90.33	3.71	3.9	5.38	0.46	0.26	0.39
FAS-UNet2026.06		95.81	97.05	92.79	94.81	96.15	90.85	6.53	3.33	4.34	1.2	0.17	0.58
Swin-Unet2026.06		94.45	92.54	88.66	90.9	88.84	84.1	3.92	5	5.85	0.46	0.71	0.98
DeepLabv3+2026.06		93.37	92.85	87.78	90.59	90.42	83.84	10.6	5.69	6.26	0.75	0.48	1