Chest Radiograph Classification on PadChest (test)
0.893AUROCConvNeXt-B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ConvNeXt-BInitialization strategy=DINOv3, Resolution=512x512, Evaluation protocol=full fine-tuning2025.10 | 0.893 | — | |
| ViT-BInitialization strategy=DINOv3, Resolution=512x512, Evaluation protocol=full fine-tuning2025.10 | 0.889 | — | |
| ViT-BInitialization strategy=DINOv2, Resolution=512x512, Evaluation protocol=full fine-tuning2025.10 | 0.885 | 0.006 | |
| ConvNeXt-BInitialization strategy=ImageNet, Resolution=512x512, Evaluation protocol=full fine-tuning2025.10 | 0.885 | 0.001 | |
| ViT-BInitialization strategy=DINOv2, Resolution=224x224, Evaluation protocol=full fine-tuning2025.10 | 0.88 | 0.006 | |
| ConvNeXt-BInitialization strategy=DINOv3, Resolution=224x224, Evaluation protocol=full fine-tuning2025.10 | 0.88 | — | |
| ViT-BInitialization strategy=ImageNet, Resolution=512x512, Evaluation protocol=full fine-tuning2025.10 | 0.876 | 0.006 | |
| ConvNeXt-BInitialization strategy=ImageNet, Resolution=224x224, Evaluation protocol=full fine-tuning2025.10 | 0.875 | 0.001 | |
| ViT-BInitialization strategy=DINOv3, Resolution=224x224, Evaluation protocol=full fine-tuning2025.10 | 0.874 | — | |
| ViT-BInitialization strategy=ImageNet, Resolution=224x224, Evaluation protocol=full fine-tuning2025.10 | 0.87 | 0.012 |