List your company
ResearchFormerly WizWand

Medical Image Classification on COVIDx

95.2AccuracyMed-UniC (ViT-L/32)
48.71260.78172.8584.919May 31, 2023
Updated 8mo ago

Evaluation results

MethodLinks
Med-UniC (ViT-L/32)Backbone=ViT-L/32, Training Data=100%, Protocol=Linear classification2023.0595.2
Med-UniC (ViT-B/16)Backbone=ViT-B/16, Training Data=100%, Protocol=Linear classification2023.0594.5
Med-UniC (ResNet-50)Backbone=ResNet-50, Training Data=100%, Protocol=Linear classification2023.0592.8
MGCA*Backbone=ViT-B/16, Training Data=100%, Protocol=Linear classification, disease-level annotations=true2023.0592.3
ConVIRTBackbone=ResNet-50, Training Data=100%, Protocol=Linear classification2023.0592
Med-UniC (ViT-L/32)Backbone=ViT-L/32, Training Data=10%, Protocol=Linear classification2023.0591.8
MRMBackbone=ViT, Training Data=100%, Protocol=Linear classification2023.0590.8
MGCA*Backbone=ResNet-50, Training Data=100%, Protocol=Linear classification, disease-level annotations=true2023.0590.5
MedKLIP*Backbone=ResNet-50, Training Data=100%, Protocol=Linear classification, disease-level annotations=true2023.0590.3
Med-UniC (ViT-B/16)Backbone=ViT-B/16, Training Data=10%, Protocol=Linear classification2023.0589.5
GLoRIABackbone=ResNet-50, Training Data=100%, Protocol=Linear classification2023.0589
Med-UniC (ResNet-50)Backbone=ResNet-50, Training Data=10%, Protocol=Linear classification2023.0589
GLoRIA-MIMICBackbone=ResNet-50, Training Data=100%, Protocol=Linear classification2023.0588.8
ImageNet InitTraining Data=100%, Protocol=Linear classification2023.0586.3
MedKLIP*Backbone=ResNet-50, Training Data=10%, Protocol=Linear classification, disease-level annotations=true2023.0585.2
MGCA*Backbone=ViT-B/16, Training Data=10%, Protocol=Linear classification, disease-level annotations=true2023.0584.8
MGCA*Backbone=ResNet-50, Training Data=10%, Protocol=Linear classification, disease-level annotations=true2023.0583.5
ConVIRTBackbone=ResNet-50, Training Data=10%, Protocol=Linear classification2023.0582.5
Med-UniC (ViT-L/32)Backbone=ViT-L/32, Training Data=1%, Protocol=Linear classification2023.0581.5
GLoRIA-MIMICBackbone=ResNet-50, Training Data=10%, Protocol=Linear classification2023.0580.5
Med-UniC (ViT-B/16)Backbone=ViT-B/16, Training Data=1%, Protocol=Linear classification2023.0580.3
MRMBackbone=ViT, Training Data=10%, Protocol=Linear classification2023.0579.3
ImageNet InitTraining Data=10%, Protocol=Linear classification2023.0578.8
GLoRIABackbone=ResNet-50, Training Data=10%, Protocol=Linear classification2023.0577.8
Med-UniC (ResNet-50)Backbone=ResNet-50, Training Data=1%, Protocol=Linear classification2023.0576.5
MGCA*Backbone=ViT-B/16, Training Data=1%, Protocol=Linear classification, disease-level annotations=true2023.0574.8
MedKLIP*Backbone=ResNet-50, Training Data=1%, Protocol=Linear classification, disease-level annotations=true2023.0574.5
ConVIRTBackbone=ResNet-50, Training Data=1%, Protocol=Linear classification2023.0572.5
MGCA*Backbone=ResNet-50, Training Data=1%, Protocol=Linear classification, disease-level annotations=true2023.0572
Random InitTraining Data=100%, Protocol=Linear classification2023.0570
GLoRIABackbone=ResNet-50, Training Data=1%, Protocol=Linear classification2023.0567.3
MRMBackbone=ViT, Training Data=1%, Protocol=Linear classification2023.0566.9
GLoRIA-MIMICBackbone=ResNet-50, Training Data=1%, Protocol=Linear classification2023.0566.5
ImageNet InitTraining Data=1%, Protocol=Linear classification2023.0564.8
Random InitTraining Data=10%, Protocol=Linear classification2023.0560.3
Random InitTraining Data=1%, Protocol=Linear classification2023.0550.5