List your company
ResearchFormerly WizWand

Image Classification on CIFAR10 (test) (Robustness & Clean Accuracy)

92.97Robust AccuracyCore-tuning
1.03424.90248.7772.638Feb 12, 2021
Updated 8mo ago

Evaluation results

MethodLinks
Core-tuningAttack type=l2, Epsilon=0.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0292.9796.82
Core-tuningAttack type=l2, Epsilon=1.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0292.3296.9
Core-tuningAttack type=l2, Epsilon=2.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0292.0596.87
AT-CE-ConAttack type=l2, Epsilon=0.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0290.7494.71
AT-CE-ConAttack type=l2, Epsilon=1.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0290.2994.8
AT-CE-ConAttack type=l2, Epsilon=2.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0289.794.27
AT-CEAttack type=l2, Epsilon=1.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0289.694.28
AT-CEAttack type=l2, Epsilon=2.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0289.1694.15
Core-tuningAttack type=linf, Epsilon=2/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0286.9296.29
AT-CEAttack type=l2, Epsilon=0.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0286.5992
AT-CE-ConAttack type=linf, Epsilon=2/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0285.0794.56
AT-CEAttack type=linf, Epsilon=2/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0283.293.05
Core-tuningAttack type=linf, Epsilon=4/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0282.0195.95
AT-CE-ConAttack type=linf, Epsilon=4/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0279.7593.79
AT-CEAttack type=linf, Epsilon=4/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0275.8291.99
Core-tuningAttack type=linf, Epsilon=8/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0274.8395.9
AT-CE-ConAttack type=linf, Epsilon=8/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0270.793.38
AT-CEAttack type=linf, Epsilon=8/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0269.2792.79
CEAttack type=l2, Epsilon=0.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0250.2594.7
CEAttack type=l2, Epsilon=1.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0248.2994.7
CEAttack type=l2, Epsilon=2.5, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0246.8294.7
CEAttack type=linf, Epsilon=2/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0225.1394.7
CEAttack type=linf, Epsilon=4/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.0212.2894.7
CEAttack type=linf, Epsilon=8/255, Attack method=PGD-10, Backbone=ResNet-50, Pre-training=MoCo-v22021.024.5794.7