Image Classification on CIFAR-10-LT λ=50 (test)
0.1464Error RateHybrid-PSC
Evaluation results
| Method | Links | |
|---|---|---|
| Hybrid-PSCBackbone=ResNet-322021.12 | 0.1464 | |
| RISDABackbone=ResNet-322021.12 | 0.1576 | |
| MetaSAug with cross-entropy lossBackbone=ResNet-322021.12 | 0.1597 | |
| Bag of TricksBackbone=ResNet-322021.12 | 0.1641 | |
| BBNBackbone=ResNet-322021.12 | 0.1782 | |
| Meta-class-weight with cross-entropy lossBackbone=ResNet-322021.12 | 0.1949 | |
| Meta-weight netBackbone=ResNet-322021.12 | 0.209 | |
| Class-balanced CEBackbone=ResNet-322021.12 | 0.2187 | |
| MixupBackbone=ResNet-322021.12 | 0.2218 | |
| Class-balanced fine-tuningBackbone=ResNet-322021.12 | 0.2256 | |
| L2RWBackbone=ResNet-322021.12 | 0.2355 | |
| Cross-EntropyBackbone=ResNet-322021.12 | 0.2506 |