Image Classification on CIFAR-100 (test) (AA and SA Metrics)
25.34Average Accuracy (AA)DynACL-AIR
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DynACL-AIRPre-training=DynACL-AIR, Finetuning=Adversarial Full Finetuning (AFF), Backbone=ResNet-182023.04 | 25.34 | 57.44 | |
| ACL-AIRPre-training=ACL-AIR, Finetuning=Adversarial Full Finetuning (AFF), Backbone=ResNet-182023.04 | 25.27 | 57.79 | |
| DynACLPre-training=DynACL, Finetuning=Adversarial Full Finetuning (AFF), Backbone=ResNet-182023.04 | 24.7 | 57.22 | |
| ACLPre-training=ACL, Finetuning=Adversarial Full Finetuning (AFF), Backbone=ResNet-182023.04 | 24.16 | 56.68 | |
| DynACL-AIRPre-training=DynACL-AIR, Finetuning=Adversarial Linear Finetuning (ALF), Backbone=ResNet-182023.04 | 21.23 | 45.63 | |
| DynACL-AIRPre-training=DynACL-AIR, Finetuning=Standard Linear Finetuning (SLF), Backbone=ResNet-182023.04 | 20.45 | 46.84 | |
| DynACLPre-training=DynACL, Finetuning=Adversarial Linear Finetuning (ALF), Backbone=ResNet-182023.04 | 20.3 | 43.58 | |
| DynACLPre-training=DynACL, Finetuning=Standard Linear Finetuning (SLF), Backbone=ResNet-182023.04 | 19.31 | 45.67 | |
| ACL-AIRPre-training=ACL-AIR, Finetuning=Adversarial Linear Finetuning (ALF), Backbone=ResNet-182023.04 | 18.68 | 47.07 | |
| ACLPre-training=ACL, Finetuning=Adversarial Linear Finetuning (ALF), Backbone=ResNet-182023.04 | 17.36 | 42.69 | |
| ACL-AIRPre-training=ACL-AIR, Finetuning=Standard Linear Finetuning (SLF), Backbone=ResNet-182023.04 | 16.14 | 49.75 | |
| ACLPre-training=ACL, Finetuning=Standard Linear Finetuning (SLF), Backbone=ResNet-182023.04 | 15.78 | 45.7 |