Medical Image Segmentation on QaTa-COV19 (test)
91.65DiceSSA
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SSAType=Multi-Modal2025.12 | 91.65 | 84.6 | — | |
| MLMoEType=Multi-Modal2025.12 | 91.19 | 83.81 | — | |
| MMI-UNetType=Multi-Modal2025.12 | 90.88 | 83.28 | — | |
| TMCACategory=Language-guided2024.12 | 90.87 | 83.27 | — | |
| HCFNetCategory=Language-guided2024.12 | 90.75 | 83.06 | — | |
| Our MethodModality=Multi-Modal, Use Text Prompt=true, Text Embedding Encoder=CXR-BERT2023.07 | 89.78 | 81.45 | 97.52 | |
| GuideDecoderType=Multi-Modal2025.12 | 89.78 | 81.45 | — | |
| AriadneCategory=Language-guided2024.12 | 89.78 | 81.45 | — | |
| EviVLMCategory=Language-guided2024.12 | 85.79 | 77.34 | — | |
| RecLMISCategory=Language-guided2024.12 | 85.22 | 77 | — | |
| CausalCLIPSegModality=Multi-modal2025.03 | 85.21 | 76.9 | — | |
| LViTModality=Multi-Modal, Use Text Prompt=true, Text Embedding Encoder=CXR-BERT2023.07 | 84.92 | 73.79 | 96.24 | |
| LViTCategory=Language-guided2024.12 | 84.92 | 73.79 | — | |
| nnU-NetType=Mono-Modal2025.12 | 84.39 | 72.35 | — | |
| Unet++Modality=Mono-Modal, Use Text Prompt=false2023.07 | 83.69 | 71.96 | 96.08 | |
| U-Net++Category=Image-only2024.12 | 83.69 | 71.96 | — | |
| LViT-TBackbone=Hybrid, Text information=true, Label ratio=100%, Param (M)=29.7, Flops (G)=54.12022.06 | 83.66 | 75.11 | — | |
| LVITModality=Multi-modal2025.03 | 83.66 | 75.11 | — | |
| U-Net++Type=Mono-Modal2025.12 | 83.66 | 71.91 | — | |
| LViTType=Multi-Modal2025.12 | 83.66 | 75.11 | — | |
| U-NetType=Mono-Modal2025.12 | 83.52 | 71.71 | — | |
| UnetModality=Mono-Modal, Use Text Prompt=false2023.07 | 82.99 | 70.92 | 95.84 | |
| U-NetCategory=Image-only2024.12 | 82.99 | 70.92 | — | |
| LViT-TBackbone=Hybrid, Text information=true, Label ratio=50%, Param (M)=29.7, Flops (G)=54.12022.06 | 82.73 | 73.99 | — | |
| Attention UnetModality=Mono-Modal, Use Text Prompt=false2023.07 | 82.4 | 70.06 | 95.67 | |
| Attention U-NetCategory=Image-only2024.12 | 82.4 | 70.06 | — | |
| AttentionUnetType=Mono-Modal2025.12 | 82.13 | 69.67 | — | |
| LViT-TWBackbone=Hybrid, Text information=false, Label ratio=100%, Param (M)=28, Flops (G)=542022.06 | 81.12 | 71.37 | — | |
| LViT-TBackbone=Hybrid, Text information=true, Label ratio=25%, Param (M)=29.7, Flops (G)=54.12022.06 | 80.95 | 71.31 | — | |
| nnUNetBackbone=CNN, Text information=false, Label ratio=100%, Param (M)=19.1, Flops (G)=412.72022.06 | 80.42 | 70.81 | — | |
| nnUNetModality=Uni-modal2025.03 | 80.42 | 70.81 | — | |
| Swin UNETRType=Mono-Modal2025.12 | 80.42 | 67.25 | — | |
| nnU-NetCategory=Image-only2024.12 | 80.42 | 70.81 | — | |
| LViT-TWBackbone=Hybrid, Text information=false, Label ratio=50%, Param (M)=28, Flops (G)=542022.06 | 80.35 | 70.74 | — | |
| Swin UNETRModality=Mono-Modal, Use Text Prompt=false2023.07 | 80.02 | 66.69 | 95.11 | |
| GLORIABackbone=Hybrid, Text information=true, Label ratio=100%, Param (M)=45.6, Flops (G)=60.82022.06 | 79.94 | 70.68 | — | |
| GLORIAModality=Multi-modal2025.03 | 79.94 | 70.68 | — | |
| GloRIACategory=VLP-based2024.12 | 79.94 | 70.68 | — | |
| TGANetBackbone=CNN, Text information=true, Label ratio=100%, Param (M)=19.8, Flops (G)=41.92022.06 | 79.87 | 70.75 | — | |
| TGANetModality=Multi-modal2025.03 | 79.87 | 70.75 | — | |
| TGANetCategory=Language-guided2024.12 | 79.87 | 70.75 | — | |
| CLIPBackbone=Hybrid, Text information=true, Label ratio=100%, Param (M)=87, Flops (G)=105.32022.06 | 79.81 | 70.66 | — | |
| CLIPCategory=VLP-based2024.12 | 79.81 | 70.66 | — | |
| ConVIRTBackbone=CNN, Text information=true, Label ratio=100%, Param (M)=35.2, Flops (G)=44.62022.06 | 79.72 | 70.58 | — | |
| ConVIRTModality=Multi-modal2025.03 | 79.72 | 70.58 | — | |
| ViLTBackbone=Hybrid, Text information=true, Label ratio=100%, Param (M)=87.4, Flops (G)=55.92022.06 | 79.63 | 70.12 | — | |
| ViLTModality=Multi-modal2025.03 | 79.63 | 70.12 | — | |
| UNet++Backbone=CNN, Text information=false, Label ratio=100%, Param (M)=74.5, Flops (G)=94.62022.06 | 79.62 | 70.25 | — | |
| UNet++Modality=Uni-modal2025.03 | 79.62 | 70.25 | — | |
| AttUNetBackbone=CNN, Text information=false, Label ratio=100%, Param (M)=34.9, Flops (G)=101.92022.06 | 79.31 | 70.04 | — | |
| AttUNetModality=Uni-modal2025.03 | 79.31 | 70.04 | — | |
| LAVTBackbone=Hybrid, Text information=true, Label ratio=100%, Param (M)=118.6, Flops (G)=83.82022.06 | 79.28 | 69.89 | — | |
| LAVTModality=Multi-modal2025.03 | 79.28 | 69.89 | — | |
| UCTransNetBackbone=Hybrid, Text information=false, Label ratio=100%, Param (M)=65.6, Flops (G)=63.22022.06 | 79.15 | 69.6 | — | |
| UCTransNetModality=Uni-modal2025.03 | 79.15 | 69.6 | — | |
| LViT-TWBackbone=Hybrid, Text information=false, Label ratio=25%, Param (M)=28, Flops (G)=542022.06 | 79.08 | 69.42 | — | |
| U-NetBackbone=CNN, Text information=false, Label ratio=100%, Param (M)=14.8, Flops (G)=50.32022.06 | 79.02 | 69.46 | — | |
| U-NetModality=Uni-modal2025.03 | 79.02 | 69.46 | — | |
| TransUNetBackbone=Hybrid, Text information=false, Label ratio=100%, Param (M)=105, Flops (G)=56.72022.06 | 78.63 | 69.13 | — | |
| TransUnetModality=Uni-modal2025.03 | 78.63 | 69.13 | — | |
| Swin-UnetBackbone=Hybrid, Text information=false, Label ratio=100%, Param (M)=82.3, Flops (G)=67.32022.06 | 78.07 | 68.34 | — | |
| Swin-UnetModality=Uni-modal2025.03 | 78.07 | 68.34 | — |