Image Classification on CIFAR-LT-100 Imbalance Factor 200 (test)
56.91Top-1 ErrorMetaSAug with LDAM loss
Evaluation results
| Method | Links | |
|---|---|---|
| MetaSAug with LDAM lossBackbone=ResNet-32, Imbalance factor=2002021.03 | 56.91 | |
| MetaSAug with focal lossBackbone=ResNet-32, Imbalance factor=2002021.03 | 59.78 | |
| MetaSAug with cross-entropy lossBackbone=ResNet-32, Imbalance factor=2002021.03 | 60.06 | |
| Meta-class-weight with LDAM lossBackbone=ResNet-32, Imbalance factor=2002021.03 | 60.47 | |
| Meta-class-weight with focal lossBackbone=ResNet-32, Imbalance factor=2002021.03 | 60.66 | |
| Meta-class-weight with cross-entropy lossBackbone=ResNet-32, Imbalance factor=2002021.03 | 60.69 | |
| Class-balanced fine-tuningBackbone=ResNet-32, Imbalance factor=2002021.03 | 61.34 | |
| LDAM-DRWBackbone=ResNet-32, Imbalance factor=2002021.03 | 61.55 | |
| Meta-weight netBackbone=ResNet-32, Imbalance factor=2002021.03 | 63.38 | |
| LDAM lossBackbone=ResNet-32, Imbalance factor=2002021.03 | 63.47 | |
| Class-balanced focal lossBackbone=ResNet-32, Imbalance factor=2002021.03 | 63.77 | |
| Focal lossBackbone=ResNet-32, Imbalance factor=2002021.03 | 64.38 | |
| Class-balanced cross-entropy lossBackbone=ResNet-32, Imbalance factor=2002021.03 | 64.44 | |
| Cross-entropy trainingBackbone=ResNet-32, Imbalance factor=2002021.03 | 65.3 | |
| L2RWBackbone=ResNet-32, Imbalance factor=2002021.03 | 67 |