Image Classification on CIFAR-LT-100 Imbalance Factor 20 (test)
42.15Top-1 ErrorMetaSAug with cross-entropy loss
Evaluation results
| Method | Links | |
|---|---|---|
| MetaSAug with cross-entropy lossBackbone=ResNet-32, Imbalance factor=202021.03 | 42.15 | |
| MetaSAug with focal lossBackbone=ResNet-32, Imbalance factor=202021.03 | 42.41 | |
| MetaSAug with LDAM lossBackbone=ResNet-32, Imbalance factor=202021.03 | 42.47 | |
| Meta-class-weight with focal lossBackbone=ResNet-32, Imbalance factor=202021.03 | 44.27 | |
| Meta-class-weight with cross-entropy lossBackbone=ResNet-32, Imbalance factor=202021.03 | 44.38 | |
| Meta-weight netBackbone=ResNet-32, Imbalance factor=202021.03 | 46.96 | |
| LDAM-DRWBackbone=ResNet-32, Imbalance factor=202021.03 | 47.01 | |
| Class-balanced focal lossBackbone=ResNet-32, Imbalance factor=202021.03 | 47.41 | |
| Meta-class-weight with LDAM lossBackbone=ResNet-32, Imbalance factor=202021.03 | 47.62 | |
| Class-balanced fine-tuningBackbone=ResNet-32, Imbalance factor=202021.03 | 47.7 | |
| Focal lossBackbone=ResNet-32, Imbalance factor=202021.03 | 48.05 | |
| Class-balanced cross-entropy lossBackbone=ResNet-32, Imbalance factor=202021.03 | 48.06 | |
| LDAM lossBackbone=ResNet-32, Imbalance factor=202021.03 | 48.41 | |
| Cross-entropy trainingBackbone=ResNet-32, Imbalance factor=202021.03 | 48.94 | |
| L2RWBackbone=ResNet-32, Imbalance factor=202021.03 | 49.25 |