Selective Classification on ImageNet-Sketch (Original Test)
58.4Metric AMDS
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MDSBackbone=ResNet-50, Training Dataset=ImageNet-1K, Pre-training Source=Official PyTorch Repository2025.05 | 58.4 | 119 | |
| SIRCBackbone=ResNet-50, Training Dataset=ImageNet-1K, Pre-training Source=Official PyTorch Repository2025.05 | 46.2 | 84.4 | |
| KNNBackbone=ResNet-50, Training Dataset=ImageNet-1K, Pre-training Source=Official PyTorch Repository2025.05 | 40.2 | 67.3 | |
| Δ-KNNBackbone=ResNet-50, Training Dataset=ImageNet-1K, Pre-training Source=Official PyTorch Repository2025.05 | 36 | 55.2 | |
| Δ-MDSBackbone=ResNet-50, Training Dataset=ImageNet-1K, Pre-training Source=Official PyTorch Repository2025.05 | 30.3 | 39 | |
| EnergyBackbone=ResNet-50, Training Dataset=ImageNet-1K, Pre-training Source=Official PyTorch Repository2025.05 | 28.1 | 32.8 | |
| MaxLogitBackbone=ResNet-50, Training Dataset=ImageNet-1K, Pre-training Source=Official PyTorch Repository2025.05 | 25.3 | 24.8 | |
| RLogBackbone=ResNet-50, Training Dataset=ImageNet-1K, Pre-training Source=Official PyTorch Repository2025.05 | 24.5 | 22.5 | |
| Δ-KNN-RLogBackbone=ResNet-50, Training Dataset=ImageNet-1K, Pre-training Source=Official PyTorch Repository2025.05 | 24.3 | 22.1 | |
| Δ-MDS-RLogBackbone=ResNet-50, Training Dataset=ImageNet-1K, Pre-training Source=Official PyTorch Repository2025.05 | 24.1 | 21.5 | |
| MSPBackbone=ResNet-50, Training Dataset=ImageNet-1K, Pre-training Source=Official PyTorch Repository2025.05 | 23.4 | 19.6 |