Image Classification on CIFAR-100 IR=10, NR=0.0 (test)
36.7Top-1 Error Rateλ^{A,W,S}
Evaluation results
| Method | Links | |
|---|---|---|
| λ^{A,W,S}Backbone=WRNet28-10, Configuration=per-point augmentation + loss reweighting + soft-labeling2021.03 | 36.7 | |
| λ^{A,W}Backbone=WRNet28-10, Configuration=per-point augmentation + loss reweighting2021.03 | 39 | |
| FAABackbone=WRNet28-102021.03 | 40 | |
| λ^ABackbone=WRNet28-10, Configuration=per-point augmentation hyperparameters2021.03 | 40.8 | |
| λ^{ASHA}Backbone=WRNet28-10, Configuration=shared augmentation hyperparameters2021.03 | 41 | |
| DADABackbone=WRNet28-102021.03 | 41.1 | |
| RAABackbone=WRNet28-102021.03 | 41.7 | |
| BaselineBackbone=WRNet28-102021.03 | 45.9 |