Medical Image Segmentation on QaTa-COV19
84.95mIoUTAMISeg
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| TAMISegBackbone=CNN, Params ↓ (M)=48.75, FLOPs ↓ (G)=29.83, Multi-modal=true2026.04 | 84.95 | 91.79 | — | — | — | — | |
| FMISegBackbone=CNN, Text=Yes2025.09 | 83.84 | 91.21 | — | — | — | — | |
| MedSegDiff-V2Backbone=Diffusion, Params ↓ (M)=46.12, FLOPs ↓ (G)=149.01, Multi-modal=false2026.04 | 83.04 | 90.81 | — | — | — | — | |
| TGCAMBackbone=CNN, Text=Yes2025.09 | 82.81 | 90.6 | — | — | — | — | |
| BiCLIPText-Guided=Yes, Backbone=CNN2026.02 | 82.81 | 90.59 | — | — | — | — | |
| ProLearnBackbone=CNN, Params ↓ (M)=69.88, FLOPs ↓ (G)=38.12, Multi-modal=true2026.04 | 82.81 | 90.6 | — | — | — | — | |
| TGC-NetText-enhanced=true2025.12 | 82.71 | 90.54 | — | — | — | — | |
| EF-UNetVenue=arXiv’25, Text-Guided=Yes, Backbone=CNN2026.02 | 82.58 | 90.46 | — | — | — | — | |
| MAdapterBackbone=CNN, Text=Yes2025.09 | 82.16 | 90.22 | — | — | — | — | |
| MAdapterBackbone=CNN, Params ↓ (M)=67.55, FLOPs ↓ (G)=37.65, Multi-modal=true2026.04 | 82.16 | 90.22 | — | — | — | — | |
| LanGuideSegModality=Multi-Modal2024.09 | 81.5 | 89.8 | 97.5 | — | — | — | |
| LanGuideSegBackbone=CNN, Text=Yes2025.09 | 81.45 | 89.78 | — | — | — | — | |
| Ariadne’s ThreadVenue=MICCAI’23, Text-enhanced=true2025.12 | 81.45 | 89.78 | — | — | — | — | |
| LanGuideSegBackbone=CNN, Params ↓ (M)=64.35, FLOPs ↓ (G)=36.27, Multi-modal=true2026.04 | 81.45 | 89.78 | — | — | — | — | |
| ConDSegBackbone=CNN, Params ↓ (M)=43.81, FLOPs ↓ (G)=28.62, Multi-modal=false2026.04 | 78.38 | 89.76 | — | — | — | — | |
| SwinTextUNet2026.04 | 78.2 | 86.47 | — | — | — | — | |
| TextDiffBackbone=Diffusion, Params ↓ (M)=9.68, FLOPs ↓ (G)=36.85, Multi-modal=true2026.04 | 77.91 | 80.86 | — | — | — | — | |
| SGSegBackbone=CNN, Text=Yes2025.09 | 77.82 | 87.41 | — | — | — | — | |
| TGCAMBackbone=CNN, Params ↓ (M)=61.76, FLOPs ↓ (G)=35.99, Multi-modal=true2026.04 | 77.82 | 87.41 | — | — | — | — | |
| SGSegModality=Multi-Modal Train, Uni-Modal Inference2024.09 | 77.8 | 87.4 | 97.1 | — | — | — | |
| RecLMISBackbone=CNN, Text=Yes2025.09 | 77 | 85.22 | — | — | — | — | |
| RecLMISVenue=TMI’24, Text-enhanced=true2025.12 | 77 | 85.22 | — | — | — | — | |
| RecLMISVenue=IEEE TMI’24, Text-Guided=Yes, Backbone=CNN2026.02 | 77 | 85.22 | — | — | — | — | |
| TVE-NetBackbone=CNN, Params ↓ (M)=56.26, FLOPs ↓ (G)=33.46, Multi-modal=true2026.04 | 77 | 85.22 | — | — | — | — | |
| CausalCLIPSegBackbone=Hybrid, Text=Yes2025.09 | 76.9 | 85.21 | — | — | — | — | |
| CausalCLIPSegBackbone=Hybrid, Params ↓ (M)=89.86, FLOPs ↓ (G)=45.95, Multi-modal=true2026.04 | 76.9 | 85.21 | — | — | — | — | |
| TIRNetParams (M)=41.10, Flops (G)=24.1, Modality=multi-modal2026.06 | 76.47 | — | — | 84.77 | 91.23 | 83.88 | |
| SMF-netVenue=Frontiers’25, Text-Guided=Yes, Backbone=Hybrid2026.02 | 76.45 | 85.78 | — | — | — | — | |
| LGABackbone=Transformer, Text=Yes2025.09 | 76.23 | 84.65 | — | — | — | — | |
| LGAVenue=MICCAI’24, Text-enhanced=true2025.12 | 76.23 | 84.65 | — | — | — | — | |
| LGAVenue=MICCAI’24, Text-Guided=Yes, Backbone=ViT2026.02 | 76.23 | 84.65 | — | — | — | — | |
| LGABackbone=Transformer, Params ↓ (M)=97.58, FLOPs ↓ (G)=48.23, Multi-modal=true2026.04 | 76.23 | 84.65 | — | — | — | — | |
| MedLangViTVenue=Electronics’25, Text-Guided=Yes, Backbone=Hybrid2026.02 | 75.93 | 84.27 | — | — | — | — | |
| LViT2026.04 | 75.71 | 83.66 | — | — | — | — | |
| TeViAParams (M)=146.80, Flops (G)=11.2, Modality=multi-modal2026.06 | 75.69 | — | — | 84.12 | 90.96 | 83.41 | |
| RefSegformerVenue=TIP’24, Text-enhanced=true2025.12 | 75.48 | 84.09 | — | — | — | — | |
| LViT-TBackbone=Hybrid, Text=Yes2025.09 | 75.11 | 83.66 | — | — | — | — | |
| LVITVenue=TMI’23, Text-enhanced=true2025.12 | 75.11 | 83.66 | — | — | — | — | |
| LViTVenue=IEEE TMI’23, Text-Guided=Yes, Backbone=Hybrid2026.02 | 75.11 | 83.66 | — | — | — | — | |
| LViTBackbone=Hybrid, Params ↓ (M)=93.16, FLOPs ↓ (G)=46.75, Multi-modal=true2026.04 | 75.11 | 83.66 | — | — | — | — | |
| LVITModality=Multi-Modal2024.09 | 75.1 | 83.7 | 96.2 | — | — | — | |
| LViTParams (M)=29.70, Flops (G)=54.1, Modality=multi-modal2026.06 | 74.78 | — | — | 83.4 | 90.63 | 82.86 | |
| LGAParams (M)=8.24, Flops (G)=381.1, Modality=multi-modal2026.06 | 74.5 | — | — | 83.46 | 89.85 | 81.56 | |
| ARsegVenue=MICCAI’25, Text-enhanced=true2025.12 | 72.64 | 84.09 | — | — | — | — | |
| ARSegVenue=MICCAI’25, Text-Guided=Yes, Backbone=Hybrid2026.02 | 72.64 | 84.09 | — | — | — | — | |
| Swin U-NetModality=Uni-Modal2024.09 | 72.4 | 83.2 | 95 | — | — | — | |
| VT-MFLVVenue=Imaging’25, Text-Guided=Yes, Backbone=CNN2026.02 | 72.09 | 83.34 | — | — | — | — | |
| Cap2SegVenue=Frontiers’24, Text-Guided=Yes, Backbone=Hybrid2026.02 | 71.61 | 81.32 | — | — | — | — | |
| CERSText=Yes, Backbone=ConvNeXt, Labeled ratio=100%2026.06 | 71.6 | 81.4 | — | — | — | — | |
| CERSText=Yes, Backbone=ConvNeXt, Labeled ratio=50%2026.06 | 71.42 | 81.23 | — | — | — | — | |
| TGANetParams (M)=19.80, Flops (G)=41.9, Modality=multi-modal2026.06 | 71.24 | — | — | 80.41 | 88.45 | 79.29 | |
| nnUnetBackbone=CNN, Text=No2025.09 | 70.81 | 80.42 | — | — | — | — | |
| nnUNetVenue=Nature’21, Text-enhanced=false2025.12 | 70.81 | 80.42 | — | — | — | — | |
| nnU-NetVenue=Nature’21, Text-Guided=No, Backbone=CNN2026.02 | 70.81 | 80.42 | — | — | — | — | |
| nnU-NetBackbone=CNN, Params ↓ (M)=41.25, FLOPs ↓ (G)=32.71, Multi-modal=false2026.04 | 70.81 | 80.42 | — | — | — | — | |
| TGANetVenue=MICCAI’22, Text-enhanced=true2025.12 | 70.75 | 79.87 | — | — | — | — | |
| TGANetVenue=MICCAI’22, Text-Guided=Yes, Backbone=CNN2026.02 | 70.75 | 79.87 | — | — | — | — | |
| GLoRIAVenue=ICCV’21, Text-enhanced=true2025.12 | 70.68 | 79.94 | — | — | — | — | |
| CLIP2026.04 | 70.66 | 79.81 | — | — | — | — | |
| U-Net++Modality=Uni-Modal2024.09 | 70.6 | 82.3 | 94.7 | — | — | — | |
| CERSText=Yes, Backbone=ConvNeXt, Labeled ratio=25%2026.06 | 70.52 | 80.52 | — | — | — | — | |
| GLoRIAParams (M)=45.60, Flops (G)=60.8, Modality=multi-modal2026.06 | 70.36 | — | — | 79.51 | 88.25 | 78.97 | |
| UNet++Backbone=CNN, Text=No2025.09 | 70.25 | 79.62 | — | — | — | — | |
| U-Net++Venue=MICCAI’18, Text-enhanced=false2025.12 | 70.25 | 79.62 | — | — | — | — | |
| UNet++Venue=MICCAI’18, Text-Guided=No, Backbone=CNN2026.02 | 70.25 | 79.62 | — | — | — | — | |
| Attention U-Net2026.04 | 70.25 | 79.62 | — | — | — | — | |
| U-Net++Backbone=CNN, Params ↓ (M)=36.01, FLOPs ↓ (G)=25.22, Multi-modal=false2026.04 | 70.25 | 79.62 | — | — | — | — | |
| U-Net++Params (M)=74.50, Flops (G)=94.6, Modality=uni-modal2026.06 | 70.21 | — | — | 79.55 | 87.76 | 78.19 | |
| ViLTVenue=ICML’21, Text-enhanced=true2025.12 | 70.12 | 79.63 | — | — | — | — | |
| Attention U-NetModality=Uni-Modal2024.09 | 70.1 | 82.2 | 94.5 | — | — | — | |
| LAVTVenue=CVPR’22, Text-enhanced=true2025.12 | 69.89 | 79.28 | — | — | — | — | |
| LAVTVenue=CVPR’22, Text-Guided=Yes, Backbone=Hybrid2026.02 | 69.89 | 79.28 | — | — | — | — | |
| CMIRNetParams (M)=239.80, Flops (G)=134.5, Modality=multi-modal2026.06 | 69.87 | — | — | 79.63 | 87.45 | 77.71 | |
| nnUNetParams (M)=19.10, Flops (G)=412.7, Modality=uni-modal2026.06 | 69.69 | — | — | 79.13 | 87.37 | 77.57 | |
| LViTText=Yes, Backbone=LViT, Labeled ratio=50%2026.06 | 69.65 | 79.08 | — | — | — | — | |
| UCTransNetBackbone=Hybrid, Text=No2025.09 | 69.6 | 79.15 | — | — | — | — | |
| UCTransNetVenue=AAAI’22, Text-enhanced=false2025.12 | 69.6 | 79.15 | — | — | — | — | |
| UCTransNetVenue=AAAI’22, Text-Guided=No, Backbone=Hybrid2026.02 | 69.6 | 79.15 | — | — | — | — | |
| MAXFormerBackbone=Hybrid, Params ↓ (M)=68.96, FLOPs ↓ (G)=44.87, Multi-modal=false2026.04 | 69.6 | 79.15 | — | — | — | — | |
| ATParams (M)=44.00, Flops (G)=22.4, Modality=multi-modal2026.06 | 69.48 | — | — | 79.57 | 87.19 | 77.3 | |
| U-NetBackbone=CNN, Text=No2025.09 | 69.46 | 79.02 | — | — | — | — | |
| U-NetVenue=MICCAI’15, Text-enhanced=false2025.12 | 69.46 | 79.02 | — | — | — | — | |
| U-NetVenue=MICCAI’15, Text-Guided=No, Backbone=CNN2026.02 | 69.46 | 79.02 | — | — | — | — | |
| U-Net2026.04 | 69.46 | 79.02 | — | — | — | — | |
| U-NetBackbone=CNN, Params ↓ (M)=31.04, FLOPs ↓ (G)=54.75, Multi-modal=false2026.04 | 69.46 | 79.02 | — | — | — | — | |
| LAVTParams (M)=118.60, Flops (G)=83.8, Modality=multi-modal2026.06 | 69.35 | — | — | 78.87 | 87.56 | 77.88 | |
| U-NetModality=Uni-Modal2024.09 | 69.2 | 81.9 | 94.5 | — | — | — | |
| TransUNetBackbone=Hybrid, Text=No2025.09 | 69.13 | 78.63 | — | — | — | — | |
| TransUNetBackbone=Hybrid, Params ↓ (M)=104.93, FLOPs ↓ (G)=37.22, Multi-modal=false2026.04 | 69.13 | 78.63 | — | — | — | — | |
| Trans U-NetModality=Uni-Modal2024.09 | 68.7 | 80.6 | 93.9 | — | — | — | |
| U-NetParams (M)=14.80, Flops (G)=50.3, Modality=uni-modal2026.06 | 68.59 | — | — | 78.46 | 86.66 | 76.47 | |
| Swin-UnetBackbone=Hybrid, Text=No2025.09 | 68.34 | 78.07 | — | — | — | — | |
| Swin-UNetVenue=ECCV’22, Text-enhanced=false2025.12 | 68.34 | 78.07 | — | — | — | — | |
| Swin-UnetVenue=ECCV’22, Text-Guided=No, Backbone=Hybrid2026.02 | 68.34 | 78.07 | — | — | — | — | |
| Swin-UNetBackbone=Hybrid, Params ↓ (M)=62.03, FLOPs ↓ (G)=42.37, Multi-modal=false2026.04 | 68.34 | 78.07 | — | — | — | — | |
| Swin-UNetParams (M)=82.30, Flops (G)=67.3, Modality=uni-modal2026.06 | 67.55 | — | — | 77.29 | 86.44 | 76.12 | |
| LViTText=Yes, Backbone=LViT, Labeled ratio=25%2026.06 | 67.3 | 77.48 | — | — | — | — | |
| U-NetText=No, Backbone=ConvNeXt, Labeled ratio=100%2026.06 | 64.9 | 75.7 | — | — | — | — | |
| LeFeDText=No, Backbone=V-Net [12], Labeled ratio=50%2026.06 | 63.74 | 74.64 | — | — | — | — | |
| LeFeDText=No, Backbone=V-Net [12], Labeled ratio=25%2026.06 | 63.61 | 74.31 | — | — | — | — |