List your company
ResearchFormerly WizWand

Medical Image Classification on CheXpert (AUC)

91.2AUCMed-UniC (ViT-L/32)
54.69664.17373.6583.127May 31, 2023Nov 30, 2023May 31, 2024Nov 30, 2024Jun 1, 2025Dec 1, 2025Jun 3, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Med-UniC (ViT-L/32)Backbone=ViT-L/32, Training Data=100%, Protocol=Linear classification2023.0591.2
Med-UniC (ViT-B/16)Backbone=ViT-B/16, Training Data=100%, Protocol=Linear classification2023.0590.8
Med-UniC (ViT-L/32)Backbone=ViT-L/32, Training Data=10%, Protocol=Linear classification2023.0590.5
Med-UniC (ViT-L/32)Backbone=ViT-L/32, Training Data=1%, Protocol=Linear classification2023.0589.9
MGCA*Backbone=ViT-B/16, Training Data=100%, Protocol=Linear classification, disease-level annotations=true2023.0589.7
Med-UniC (ViT-B/16)Backbone=ViT-B/16, Training Data=10%, Protocol=Linear classification2023.0589.7
Med-UniC (ResNet-50)Backbone=ResNet-50, Training Data=100%, Protocol=Linear classification2023.0589.5
Med-UniC (ViT-B/16)Backbone=ViT-B/16, Training Data=1%, Protocol=Linear classification2023.0589.4
Med-UniC (ResNet-50)Backbone=ResNet-50, Training Data=10%, Protocol=Linear classification2023.0589.2
MGCA*Backbone=ViT-B/16, Training Data=10%, Protocol=Linear classification, disease-level annotations=true2023.0589.1
MGCA*Backbone=ViT-B/16, Training Data=1%, Protocol=Linear classification, disease-level annotations=true2023.0588.8
GLoRIA-MIMICBackbone=ResNet-50, Training Data=10%, Protocol=Linear classification2023.0588.7
MRMBackbone=ViT, Training Data=100%, Protocol=Linear classification2023.0588.7
MRMBackbone=ViT, Training Data=1%, Protocol=Linear classification2023.0588.5
MRMBackbone=ViT, Training Data=10%, Protocol=Linear classification2023.0588.5
MGCA*Backbone=ResNet-50, Training Data=100%, Protocol=Linear classification, disease-level annotations=true2023.0588.2
Med-UniC (ResNet-50)Backbone=ResNet-50, Training Data=1%, Protocol=Linear classification2023.0588.2
GLoRIABackbone=ResNet-50, Training Data=100%, Protocol=Linear classification2023.0588.1
GLoRIA-MIMICBackbone=ResNet-50, Training Data=100%, Protocol=Linear classification2023.0588
MGCA*Backbone=ResNet-50, Training Data=10%, Protocol=Linear classification, disease-level annotations=true2023.0588
FINOAdaptation set=MIMIC-CXR, Probing and evaluation set=CheXpert2026.0688
GLoRIABackbone=ResNet-50, Training Data=10%, Protocol=Linear classification2023.0587.8
MedKLIP*Backbone=ResNet-50, Training Data=100%, Protocol=Linear classification, disease-level annotations=true2023.0587.7
MGCA*Backbone=ResNet-50, Training Data=1%, Protocol=Linear classification, disease-level annotations=true2023.0587.6
ConVIRTBackbone=ResNet-50, Training Data=100%, Protocol=Linear classification2023.0587.3
Supervised adapt.Adaptation set=MIMIC-CXR, Probing and evaluation set=CheXpert2026.0687.3
GLoRIA-MIMICBackbone=ResNet-50, Training Data=1%, Protocol=Linear classification2023.0587.1
Frozen DINOv3Adaptation set=MIMIC-CXR, Probing and evaluation set=CheXpert2026.0687
ConVIRTBackbone=ResNet-50, Training Data=10%, Protocol=Linear classification2023.0586.8
GLoRIABackbone=ResNet-50, Training Data=1%, Protocol=Linear classification2023.0586.6
MedKLIP*Backbone=ResNet-50, Training Data=10%, Protocol=Linear classification, disease-level annotations=true2023.0586.5
MedKLIP*Backbone=ResNet-50, Training Data=1%, Protocol=Linear classification, disease-level annotations=true2023.0586.2
ConVIRTBackbone=ResNet-50, Training Data=1%, Protocol=Linear classification2023.0585.9
ImageNet InitTraining Data=100%, Protocol=Linear classification2023.0581.4
ImageNet InitTraining Data=10%, Protocol=Linear classification2023.0579.7
ImageNet InitTraining Data=1%, Protocol=Linear classification2023.0574.4
Random InitTraining Data=100%, Protocol=Linear classification2023.0565.7
Random InitTraining Data=10%, Protocol=Linear classification2023.0562.6
Random InitTraining Data=1%, Protocol=Linear classification2023.0556.1