Table 16 Cost comparison of different models.
From: Universal attention guided adversarial defense using feature pyramid and non-local mechanisms
Dataset | ImageNet-100 | CIFAR-10 | ||||||
|---|---|---|---|---|---|---|---|---|
Model | baseline_at | FPAS_at | ANL_at | boosting (FPAS,ANL) | baseline_at | FPAS_at | ANL_at | boosting (FPAS,ANL) |
Total params | 125.04M | 126.80M | 130.29M | 130.30M | 36.48M | 36.63M | 37.00M | 37.15M |
Time (one epoch) | 106m 52s | 107m 16s | 109m 41s | 110m 10s | 7m 15s | 7m 39s | 7m 29s | 7m 50s |
