Image Classification on CIFAR-100 (test) (IR=1, NR=0.0)
22.2Top-1 Error Rateλ^{A,W}
Evaluation Results
| Method | Links | |
|---|---|---|
| λ^{A,W}Backbone=WRNet28-10, Configuration=per-point augmentation + loss reweighting2021.03 | 22.2 | |
| λ^{A,W,S}Backbone=WRNet28-10, Configuration=per-point augmentation + loss reweighting + soft-labeling2021.03 | 22.4 | |
| FAABackbone=WRNet28-102021.03 | 22.7 | |
| RAABackbone=WRNet28-102021.03 | 23 | |
| DADABackbone=WRNet28-102021.03 | 23.1 | |
| λ^ABackbone=WRNet28-10, Configuration=per-point augmentation hyperparameters2021.03 | 23.1 | |
| λ^{ASHA}Backbone=WRNet28-10, Configuration=shared augmentation hyperparameters2021.03 | 24.7 | |
| BaselineBackbone=WRNet28-102021.03 | 24.9 |