List your company
ResearchFormerly WizWand

Semantic Segmentation on ISIC

71.1mIoUMPA
20.55633.67846.859.922Dec 11, 2025Dec 29, 2025Jan 16, 2026Feb 3, 2026Feb 21, 2026Mar 11, 2026Mar 30, 2026
Updated 7mo ago

Evaluation results

MethodLinks
MPAsource-training=false2026.0271.1
INSID3Encoder=DINOv3, #Param=304 M, Training Protocol=Training free: Unsupervised pre-training, Shot count=52026.0363.9
DMTNet (TaP)Version=TaP, Shot count=15-shot2025.1263.86
DMTNet (TaP)Version=TaP, Shot count=10-shot2025.1261.14
DMTNet (Decoder FT)Version=Decoder FT, Shot count=15-shot2025.1259.7
DMTNet (Vanilla)Version=Vanilla, Shot count=15-shot2025.1258.89
GF-SAM† + our debiasEncoder=DINOv3 + SAM, #Param=945 M, Training Protocol=Training free: Mask-supervised pre-training, Shot count=52026.0358.2
DMTNet (Decoder FT)Version=Decoder FT, Shot count=10-shot2025.1257.68
DMTNet (Vanilla)Version=Vanilla, Shot count=10-shot2025.1257.13
GF-SAM†Encoder=DINOv3 + SAM, #Param=945 M, Training Protocol=Training free: Mask-supervised pre-training, Shot count=52026.0356.7
DMTNet (TaP)Version=TaP, Shot count=5-shot2025.1256.03
GF-SAMEncoder=DINOv2 + SAM, #Param=945 M, Training Protocol=Training free: Mask-supervised pre-training, Shot count=52026.0355.2
TAVPSAM-based=true2026.0254.9
INSID3Encoder=DINOv3, #Param=304 M, Training Protocol=Training free, Supervision Type=Unsupervised pre-training2026.0354.4
DMTNet (Decoder FT)Version=Decoder FT, Shot count=5-shot2025.1253.98
DMTNet (Vanilla)Version=Vanilla, Shot count=5-shot2025.1253.77
DMTNet (TaP)Version=TaP, Shot count=3-shot2025.1253.27
GF-SAM† + debiasEncoder=DINOv3 + SAM, #Param=945 M, Training Protocol=Training free, Supervision Type=Mask-supervised pre-training, Debias=True2026.0351.8
GF-SAM†Encoder=DINOv3 + SAM, #Param=945 M, Training Protocol=Training free, Supervision Type=Mask-supervised pre-training2026.0350.9
DMTNet (Decoder FT)Version=Decoder FT, Shot count=3-shot2025.1250.7
DMTNet (Vanilla)Version=Vanilla, Shot count=3-shot2025.1250.01
GF-SAMEncoder=DINOv2 + SAM, #Param=945 M, Training Protocol=Training free, Supervision Type=Mask-supervised pre-training2026.0348.7
APSegSAM-based=true2026.0245.4
SegGPTEncoder=ViT, #Param=354 M, Training Protocol=Task-specific fine-tuning: Semantic + mask supervision, Shot count=52026.0345.2
MatcherEncoder=DINOv2 + SAM, #Param=945 M, Training Protocol=Training free, Supervision Type=Mask-supervised pre-training2026.0338.6
SegGPTEncoder=ViT, #Param=354 M, Training Protocol=Task-specific fine-tuning, Supervision Type=Semantic + mask supervision2026.0337.5
MatcherEncoder=DINOv2 + SAM, #Param=945 M, Training Protocol=Training free: Mask-supervised pre-training, Shot count=52026.0335
DiffewSEncoder=Stable Diffusion, #Param=890 M, Training Protocol=Task-specific fine-tuning: Semantic + mask supervision, Shot count=52026.0332.7
SINEEncoder=DINOv2, #Param=373 M, Training Protocol=Task-specific fine-tuning: Semantic + mask supervision, Shot count=52026.0328.6
DiffewSEncoder=Stable Diffusion, #Param=890 M, Training Protocol=Task-specific fine-tuning, Supervision Type=Semantic + mask supervision2026.0327.8
SINEEncoder=DINOv2, #Param=373 M, Training Protocol=Task-specific fine-tuning, Supervision Type=Semantic + mask supervision2026.0325.8
SegICEncoder=DINOv2, #Param=310 M, Training Protocol=Task-specific fine-tuning, Supervision Type=Semantic + mask supervision2026.0325.3
PerSAMSAM-based=true2026.0223.9
PerSAMEncoder=SAM, #Param=640 M, Training Protocol=Training free, Supervision Type=Mask-supervised pre-training2026.0323.9
SegIC (COCO)Encoder=DINOv2, #Param=310 M, Training Protocol=Task-specific fine-tuning, Supervision Type=Semantic + mask supervision, dataset split=COCO2026.0322.5