Long-tailed Image Classification on CIFAR-10-LT Imbalance ratio 100
82.68Top-1 AccGCL
Evaluation results
| Method | Links | |
|---|---|---|
| GCLBackbone Net=ResNet-322023.05 | 82.68 | |
| MisLASBackbone Net=ResNet-322023.05 | 82.06 | |
| Contrastive learningBackbone Net=ResNet-322023.05 | 81.4 | |
| De-confound-TDEBackbone Net=ResNet-322023.05 | 80.6 | |
| BBNBackbone Net=ResNet-322023.05 | 79.82 | |
| CE loss + mixup + cRTBackbone Net=ResNet-322023.05 | 79.15 | |
| LDAM-DRWBackbone Net=ResNet-322023.05 | 77.03 | |
| CE loss + mixupBackbone Net=ResNet-322023.05 | 72.96 | |
| CE lossBackbone Net=ResNet-322023.05 | 70.7 |