Multi-class medical image segmentation on Pelvic Collected (test) benchmark leaderboard · SOTA2 Research

Multi-class medical image segmentation on Pelvic Collected (test)

97.71Dice (Left)GUMP-Net

Evaluation Results

Method	Links
GUMP-Net2026.06		97.71	97.38	95.25	95.7	95.05	91.98	2.19	2.36	2.79	0.29	0.33	0.42
Attention U-Net2026.06		97.49	96.94	93.4	95.64	94.73	89.84	2.33	2.38	4.13	0.27	0.32	0.7
nnU-Net2026.06		97.14	96.78	93.6	94.99	94.25	90.17	2.11	2.33	4.23	0.31	0.36	0.84
FAS-UNet2026.06		97.13	96.84	91.65	95.1	94.58	87.51	3.04	3.02	5.13	0.32	0.34	0.9
U-Net2026.06		97.02	96.6	94.23	94.78	94.07	90.8	2.84	2.81	4.09	0.35	0.39	0.59
PottsMGNet2026.06		96.99	96.75	92.63	94.89	94.51	88.96	2.64	3.22	4.2	0.32	0.45	0.71
DeepLabv3+2026.06		95.91	96.41	88.98	93	93.56	84.21	5.08	4.61	5.77	0.52	0.48	1.06
Swin-Unet2026.06		94.2	94.12	88.82	89.83	89.89	83.65	4.28	4.76	5.52	0.63	0.64	1.09