ResNeXt-101 DenoiseAll

Reported on 1 benchmark across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Adversarial1 result

Adversarial DefenseonImageNet (targeted PGD, max perturbation=16)
Accuracy· 2018-12-09
40.4
best: 42.8 (ResNet-152 Denoise)
Feature Denoising for Improving Adversarial Robustness arXiv:1812.03411