Image Classification on Long-tailed CIFAR-10 Imbalance factor 0.01 (test)
82.4Top-1 AccuracyResLTS
Evaluation results
| Method | Links | |
|---|---|---|
| ResLTSOne-stage=true, Backbone=ResNet-32, Strong data augmentation=true2021.01 | 82.4 | |
| Causal NormOne-stage=true, Backbone=ResNet-322021.01 | 80.6 | |
| ResLTOne-stage=true, Backbone=ResNet-322021.01 | 80.44 | |
| BBNOne-stage=true, Backbone=ResNet-322021.01 | 79.82 | |
| ELF(LDAM)+DRWOne-stage=false, Backbone=ResNet-322021.01 | 78.1 | |
| LDAM+DRWOne-stage=false, Backbone=ResNet-322021.01 | 77.03 | |
| CE+DRWOne-stage=false, Backbone=ResNet-322021.01 | 76.34 | |
| CE+DRSOne-stage=false, Backbone=ResNet-322021.01 | 75.61 | |
| CB-FocalOne-stage=true, Backbone=ResNet-32, Strong data augmentation=true2021.01 | 74.57 | |
| LDAMOne-stage=true, Backbone=ResNet-322021.01 | 73.35 | |
| MixupOne-stage=true, Backbone=ResNet-32, Strong data augmentation=true2021.01 | 73.06 | |
| FocalOne-stage=true, Backbone=ResNet-32, Strong data augmentation=true2021.01 | 70.38 |