Image Classification on CIFAR-10N-r
91.28AccuracyIP Ensemble
Evaluation results
| Method | Links | |
|---|---|---|
| IP EnsembleBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.05 | 91.28 | |
| LiSSABackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.05 | 90.98 | |
| IPBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.05 | 90.82 | |
| DataInfBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.05 | 90.79 | |
| GEXBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.05 | 90.68 | |
| Self-LiSSABackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.05 | 90.66 | |
| EKFACBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.05 | 90.47 | |
| Self-TracInBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.05 | 90.43 | |
| Cross EntropyBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.05 | 90.25 | |
| TDABackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.05 | 89.87 | |
| TracInBackbone=ResNet-34, Pre-trained=ImageNet-1K, Removal Ratio=5%2024.05 | 88.09 |