Image Classification on RSNA (AUC)
90.8AUCMGCA
Evaluation results
| Method | Links | |
|---|---|---|
| MGCABackbone=ViT-B/16, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=100%, Pre-trained Dataset=MIMIC-CXR2024.02 | 90.8 | |
| MLIPBackbone=ViT-B/16, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=100%, Pre-trained Dataset=MIMIC-CXR2024.02 | 90.8 | |
| MLIPBackbone=ResNet-50, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=100%, Pre-trained Dataset=MIMIC-CXR2024.02 | 90.6 | |
| GLoRIA-MIMICEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=100%, Pre-trained Dataset=MIMIC-CXR2024.02 | 90.4 | |
| MLIPBackbone=ViT-B/16, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=10%, Pre-trained Dataset=MIMIC-CXR2024.02 | 90 | |
| MGCABackbone=ResNet-50, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=100%, Pre-trained Dataset=MIMIC-CXR2024.02 | 89.9 | |
| MGCABackbone=ViT-B/16, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=10%, Pre-trained Dataset=MIMIC-CXR2024.02 | 89.9 | |
| MLIPBackbone=ResNet-50, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=10%, Pre-trained Dataset=MIMIC-CXR2024.02 | 89.6 | |
| MLIPBackbone=ViT-B/16, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=1%, Pre-trained Dataset=MIMIC-CXR2024.02 | 89.3 | |
| GLoRIA-MIMICEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=10%, Pre-trained Dataset=MIMIC-CXR2024.02 | 89.2 | |
| MGCABackbone=ResNet-50, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=10%, Pre-trained Dataset=MIMIC-CXR2024.02 | 89.1 | |
| MGCABackbone=ViT-B/16, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=1%, Pre-trained Dataset=MIMIC-CXR2024.02 | 89.1 | |
| MLIPBackbone=ResNet-50, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=1%, Pre-trained Dataset=MIMIC-CXR2024.02 | 88.8 | |
| GLoRIAEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=100%, Pre-trained Dataset=CheXpert2024.02 | 88.6 | |
| MGCABackbone=ResNet-50, Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=1%, Pre-trained Dataset=MIMIC-CXR2024.02 | 88.6 | |
| GLoRIAEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=10%, Pre-trained Dataset=CheXpert2024.02 | 88 | |
| GLoRIA-MIMICEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=1%, Pre-trained Dataset=MIMIC-CXR2024.02 | 86.6 | |
| GLoRIAEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=1%, Pre-trained Dataset=CheXpert2024.02 | 86.1 | |
| ConVIRTEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=100%, Pre-trained Dataset=MIMIC-CXR2024.02 | 81.3 | |
| ConVIRTEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=10%, Pre-trained Dataset=MIMIC-CXR2024.02 | 80.1 | |
| ConVIRTEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=1%, Pre-trained Dataset=MIMIC-CXR2024.02 | 77.4 | |
| ImageNet InitEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=100%, Pre-trained Dataset=ImageNet2024.02 | 76.3 | |
| ImageNet InitEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=1%, Pre-trained Dataset=ImageNet2024.02 | 74.9 | |
| ImageNet InitEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=10%, Pre-trained Dataset=ImageNet2024.02 | 74.5 | |
| Random InitEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=100%, Pre-trained Dataset=None2024.02 | 74.1 | |
| Random InitEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=10%, Pre-trained Dataset=None2024.02 | 69.4 | |
| VSE++Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=100%, Pre-trained Dataset=CheXpert2024.02 | 67.9 | |
| Random InitEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=1%, Pre-trained Dataset=None2024.02 | 58.9 | |
| DSVEEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=100%, Pre-trained Dataset=CheXpert2024.02 | 57.8 | |
| VSE++Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=10%, Pre-trained Dataset=CheXpert2024.02 | 57.2 | |
| MLIPBackbone=ViT-B/16, Evaluation Protocol=Zero-shot, Pre-trained Dataset=MIMIC-CXR2024.02 | 53 | |
| DSVEEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=10%, Pre-trained Dataset=CheXpert2024.02 | 52.1 | |
| DSVEEvaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=1%, Pre-trained Dataset=CheXpert2024.02 | 49.7 | |
| VSE++Evaluation Protocol=Fine-tuning, Fine-tuning Data Percentage=1%, Pre-trained Dataset=CheXpert2024.02 | 49.4 | |
| MLIPBackbone=ResNet-50, Evaluation Protocol=Zero-shot, Pre-trained Dataset=MIMIC-CXR2024.02 | 42.9 | |
| MGCABackbone=ResNet-50, Evaluation Protocol=Zero-shot, Pre-trained Dataset=MIMIC-CXR2024.02 | 41 | |
| GLoRIA-MIMICEvaluation Protocol=Zero-shot, Pre-trained Dataset=MIMIC-CXR2024.02 | 40.6 | |
| GLoRIAEvaluation Protocol=Zero-shot, Pre-trained Dataset=CheXpert2024.02 | 39.2 | |
| MGCABackbone=ViT-B/16, Evaluation Protocol=Zero-shot, Pre-trained Dataset=MIMIC-CXR2024.02 | 39.2 | |
| ConVIRTEvaluation Protocol=Zero-shot, Pre-trained Dataset=MIMIC-CXR2024.02 | 34.7 | |
| VSE++Evaluation Protocol=Zero-shot, Pre-trained Dataset=CheXpert2024.02 | 19.1 | |
| DSVEEvaluation Protocol=Zero-shot, Pre-trained Dataset=CheXpert2024.02 | 18.7 |