Image Classification on CIFAR-100 (test) (Symmetric/Asymmetric Robustness)
71.23Top-1 Acc (Symmetric, 0.2)ABSGD(SCE)
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| ABSGD(SCE)Backbone=ResNet-50, Pre-trained=ImageNet, Optimizer=ABSGD, Loss Function=SCE2020.12 | 71.23 | 66.39 | 69.98 | 65.26 | |
| ABSGD(CE)Backbone=ResNet-50, Pre-trained=ImageNet, Optimizer=ABSGD, Loss Function=CE2020.12 | 70.63 | 66.23 | 70.7 | 68.16 | |
| CIW(CE)Backbone=ResNet-50, Pre-trained=ImageNet, Optimizer=CIW, Loss Function=CE2020.12 | 70.21 | 65.89 | 69.29 | 64.75 | |
| EG(SCE)Backbone=ResNet-50, Pre-trained=ImageNet, Optimizer=EG, Loss Function=SCE2020.12 | 69.53 | 65.36 | 69.61 | 67.01 | |
| CIW(SCE)Backbone=ResNet-50, Pre-trained=ImageNet, Optimizer=CIW, Loss Function=SCE2020.12 | 69.53 | 65.38 | 70.07 | 67.19 | |
| SGD(SCE)Backbone=ResNet-50, Pre-trained=ImageNet, Optimizer=SGD, Loss Function=SCE2020.12 | 68.28 | 60.72 | 69.31 | 64.22 | |
| SGD(CE)Backbone=ResNet-50, Pre-trained=ImageNet, Optimizer=SGD, Loss Function=CE2020.12 | 68.21 | 62.54 | 69.57 | 62.93 | |
| SGD(TCE)Backbone=ResNet-50, Pre-trained=ImageNet, Optimizer=SGD, Loss Function=TCE2020.12 | 65.12 | 59.61 | 67.98 | 60.88 |